Triple

T2292769
Position Surface form Disambiguated ID Type / Status
Subject Tirhuta script E51541 entity
Predicate unicodeBlockName P1445 FINISHED
Object Tirhuta
Tirhuta is a historical Brahmic script traditionally used for writing the Maithili language in the Mithila region of India and Nepal.
E254461 NE FINISHED

How this triple was built (5 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tirhuta | Statement: [Tirhuta script, unicodeBlockName, Tirhuta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tirhuta
Context triple: [Tirhuta script, unicodeBlockName, Tirhuta]
  • A. Tahawus
    Tahawus is a remote hamlet in New York’s Adirondack Mountains known for its historic iron mining operations and proximity to High Peaks wilderness areas.
  • B. Kadmat
    Kadmat is a coral island in India’s Lakshadweep archipelago, known for its white-sand beaches, clear lagoons, and vibrant marine life that make it a popular destination for snorkeling and diving.
  • C. Ubykhs
    The Ubykhs were a Northwest Caucasian ethnic group historically inhabiting the Black Sea coast near Sochi, known for their now-extinct Ubykh language with an exceptionally large consonant inventory.
  • D. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • E. Kamiros
    Kamiros is an ancient city and archaeological site on the northwest coast of Rhodes, known for its well-preserved Hellenistic ruins and grid-planned layout.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tirhuta
Triple: [Tirhuta script, unicodeBlockName, Tirhuta]
Generated description
Tirhuta is a historical Brahmic script traditionally used for writing the Maithili language in the Mithila region of India and Nepal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tirhuta
Target entity description: Tirhuta is a historical Brahmic script traditionally used for writing the Maithili language in the Mithila region of India and Nepal.
  • A. Tahawus
    Tahawus is a remote hamlet in New York’s Adirondack Mountains known for its historic iron mining operations and proximity to High Peaks wilderness areas.
  • B. Kadmat
    Kadmat is a coral island in India’s Lakshadweep archipelago, known for its white-sand beaches, clear lagoons, and vibrant marine life that make it a popular destination for snorkeling and diving.
  • C. Ubykhs
    The Ubykhs were a Northwest Caucasian ethnic group historically inhabiting the Black Sea coast near Sochi, known for their now-extinct Ubykh language with an exceptionally large consonant inventory.
  • D. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • E. Kamiros
    Kamiros is an ancient city and archaeological site on the northwest coast of Rhodes, known for its well-preserved Hellenistic ruins and grid-planned layout.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: unicodeBlockName
Context triple: [Tirhuta script, unicodeBlockName, Tirhuta]
  • A. UnicodeBlock chosen
    Indicates that a character belongs to a specific contiguous range of code points defined as a Unicode block.
  • B. hasAdditionalUnicodeBlock
    Indicates that an entity is associated with one or more supplementary Unicode character blocks beyond its primary assigned block.
  • C. hasUnicodeName
    Indicates that an entity is associated with a specific official Unicode name assigned to a character or symbol.
  • D. UnicodeStandardVersionIntroduced
    Indicates the specific version of the Unicode Standard in which a given character, feature, or property was first introduced.
  • E. characterSetName
    Indicates the name assigned to a particular character set used for encoding or representing characters.
  • F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a88b09c644819090b503456d96bf70 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abcd0e42248190ada33b84d75caa64 completed March 7, 2026, 7 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f23ca34819091d2bb0d41613b4a completed March 9, 2026, 8:04 a.m.
NEDg Description generation batch_69ae82aa6d7c81909cb770ea2be10b2a completed March 9, 2026, 8:19 a.m.
NED2 Entity disambiguation (via description) batch_69ae837e392c8190baa7552ce8c14995 completed March 9, 2026, 8:23 a.m.
PD Predicate disambiguation batch_69abc589295c819092989820c2b4e9d8 completed March 7, 2026, 6:28 a.m.
Created at: March 4, 2026, 7:48 p.m.