Triple

T19459349
Position Surface form Disambiguated ID Type / Status
Subject Ua Huka E486825 entity
Predicate hasSettlement P1068 FINISHED
Object Hane
Hane is a small coastal village on the Marquesan island of Ua Huka in French Polynesia, known for its archaeological sites and traditional Polynesian culture.
 E1376740 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: Hane | Statement: [Ua Huka, hasSettlement, Hane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hane
Context triple: [Ua Huka, hasSettlement, Hane]
  • A. Haan
    Haan is a town in the German state of North Rhine-Westphalia, known for its location between Düsseldorf and Wuppertal and its mix of residential areas and light industry.
  • B. Haan
    Haan is a music producer and member of the hip-hop and trap-focused collective Internet Money.
  • C. Hain
    Hain is an ancient, central world in Ursula K. Le Guin’s Hainish Cycle, often portrayed as the cradle of human-like civilizations across the galaxy.
  • D. Hanasand
    Hanasand is a coastal village in Norway that serves as one end of the Finnfast subsea road tunnel connection.
  • E. Hannen
    Hannen is an English surname associated with several notable figures, including actors and judges, in British history.
  • 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: Hane
Triple: [Ua Huka, hasSettlement, Hane]
Generated description
Hane is a small coastal village on the Marquesan island of Ua Huka in French Polynesia, known for its archaeological sites and traditional Polynesian culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hane
Target entity description: Hane is a small coastal village on the Marquesan island of Ua Huka in French Polynesia, known for its archaeological sites and traditional Polynesian culture.
  • A. Haan
    Haan is a town in the German state of North Rhine-Westphalia, known for its location between Düsseldorf and Wuppertal and its mix of residential areas and light industry.
  • B. Haan
    Haan is a music producer and member of the hip-hop and trap-focused collective Internet Money.
  • C. Hain
    Hain is an ancient, central world in Ursula K. Le Guin’s Hainish Cycle, often portrayed as the cradle of human-like civilizations across the galaxy.
  • D. Hanasand
    Hanasand is a coastal village in Norway that serves as one end of the Finnfast subsea road tunnel connection.
  • E. Hannen
    Hannen is an English surname associated with several notable figures, including actors and judges, in British history.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c6c55c8190965ada884f17c800 completed April 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a073b3a5ce88190a35e6b6195c5ca02 completed May 15, 2026, 3:26 p.m.
NEDg Description generation batch_6a073c0a02c8819080b0e71caf65e6fa completed May 15, 2026, 3:30 p.m.
NED2 Entity disambiguation (via description) batch_6a073d0e92d48190880317263fe6e481 completed May 15, 2026, 3:34 p.m.
Created at: April 10, 2026, 1:38 p.m.