Triple

T1284613
Position Surface form Disambiguated ID Type / Status
Subject Meso-Melanesian languages E27405 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Lihir
Lihir is an Oceanic language spoken primarily on the Lihir Islands of Papua New Guinea.
 E147940 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: Lihir | Statement: [Meso-Melanesian languages, hasMemberLanguage, Lihir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lihir
Context triple: [Meso-Melanesian languages, hasMemberLanguage, Lihir]
  • A. Heltermaa
    Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
  • B. Hyllus
    Hyllus is a figure in Greek mythology known as the son of Heracles and Deianira, often associated with the Dorian invasion and the Heracleidae.
  • C. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • D. Tumpa
    Tumpa is a song featured on the album "Legend of the Sun Virgin."
  • E. Alaior
    Alaior is a historic inland town and municipality on the Spanish island of Menorca, known for its traditional architecture and local cheese production.
  • 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: Lihir
Triple: [Meso-Melanesian languages, hasMemberLanguage, Lihir]
Generated description
Lihir is an Oceanic language spoken primarily on the Lihir Islands of Papua New Guinea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lihir
Target entity description: Lihir is an Oceanic language spoken primarily on the Lihir Islands of Papua New Guinea.
  • A. Heltermaa
    Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
  • B. Hyllus
    Hyllus is a figure in Greek mythology known as the son of Heracles and Deianira, often associated with the Dorian invasion and the Heracleidae.
  • C. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • D. Tumpa
    Tumpa is a song featured on the album "Legend of the Sun Virgin."
  • E. Alaior
    Alaior is a historic inland town and municipality on the Spanish island of Menorca, known for its traditional architecture and local cheese production.
  • 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_69a496d4ec448190ad653b2590c46711 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c0b6dda48190a2e79084adea6ec1 completed March 1, 2026, 10:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69acacba08f881909230c2d9459d4bc4 completed March 7, 2026, 10:54 p.m.
NEDg Description generation batch_69acad2bc82c81909ec4c314e4fe7cc7 completed March 7, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_69acae0dc4708190bc3a9918391e6739 completed March 7, 2026, 11 p.m.
Created at: March 1, 2026, 7:50 p.m.