Triple

T12137365
Position Surface form Disambiguated ID Type / Status
Subject Guhila dynasty E289093 entity
Predicate capital P234 FINISHED
Object Ahar
Ahar is an ancient town in present-day Rajasthan, India, historically significant as an early political and cultural center of the region.
E968165 NE FINISHED

How this triple was built (4 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: Ahar | Statement: [Guhila dynasty, capital, Ahar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ahar
Context triple: [Guhila dynasty, capital, Ahar]
  • A. Ahar
    Ahar is a historic city in northwestern Iran known as a regional center of the Azerbaijani population and a gateway to the Arasbaran forests.
  • B. Puzrish-Dagan
    Puzrish-Dagan was a major Ur III-period Mesopotamian administrative center known for its extensive archive of economic and bureaucratic cuneiform tablets.
  • C. Daimabad
    Daimabad is an archaeological site in Maharashtra, India, notable for its late Harappan (Indus Valley Civilization) remains and distinctive Bronze Age artifacts.
  • D. Tahara
    Tahara is a feminine given name, often considered a variant of Tara, used in various cultures.
  • E. Tahara
    Tahara is a coastal city in central Japan known for its automotive manufacturing industry and scenic Cape Irago on the Atsumi Peninsula.
  • 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: Ahar
Triple: [Guhila dynasty, capital, Ahar]
Generated description
Ahar is an ancient town in present-day Rajasthan, India, historically significant as an early political and cultural center of the region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ahar
Target entity description: Ahar is an ancient town in present-day Rajasthan, India, historically significant as an early political and cultural center of the region.
  • A. Ahar
    Ahar is a historic city in northwestern Iran known as a regional center of the Azerbaijani population and a gateway to the Arasbaran forests.
  • B. Puzrish-Dagan
    Puzrish-Dagan was a major Ur III-period Mesopotamian administrative center known for its extensive archive of economic and bureaucratic cuneiform tablets.
  • C. Daimabad
    Daimabad is an archaeological site in Maharashtra, India, notable for its late Harappan (Indus Valley Civilization) remains and distinctive Bronze Age artifacts.
  • D. Tahara
    Tahara is a feminine given name, often considered a variant of Tara, used in various cultures.
  • E. Tahara
    Tahara is a coastal city in central Japan known for its automotive manufacturing industry and scenic Cape Irago on the Atsumi Peninsula.
  • F. None of above. chosen

Provenance (5 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_69d6ab4b5e4c81909950b17151eb0951 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9158dd00c819082651891898b91bb completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f690ae408190966bb4fe8feaa7d2 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f6022ecf38819080f0eb6a3a815c5b completed May 2, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_69f606560934819092ba4d4fa162b799 completed May 2, 2026, 2:12 p.m.
Created at: April 8, 2026, 9:49 p.m.