Triple

T22106132
Position Surface form Disambiguated ID Type / Status
Subject Central Province, Papua New Guinea E546290 entity
Predicate containsTown P847 FINISHED
Object Kupiano NE NERFINISHED

How this triple was built (2 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: Kupiano | Statement: [Central Province, Papua New Guinea, containsTown, Kupiano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kupiano
Context triple: [Central Province, Papua New Guinea, containsTown, Kupiano]
  • A. Kupiano chosen
    Kupiano is a coastal town in Papua New Guinea’s Central Province, known as a local administrative and trading center for surrounding rural communities.
  • B. Kiepura
    Kiepura is the surname of Jan Kiepura, a renowned Polish tenor and film actor active in the early to mid-20th century.
  • C. Kipare
    Kipare is the Bantu language spoken by the Pare people of northeastern Tanzania.
  • D. Kipoi
    Kipoi is a traditional stone-built village in the Zagori region of Epirus, northwestern Greece, known for its arched bridges and well-preserved architecture.
  • E. Papingo
    Papingo is a picturesque traditional village in the Zagori region of Epirus, northwestern Greece, known for its stone architecture and dramatic mountain scenery.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12918d7a4819080283c287a253c9f completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.