Triple

T1202745
Position Surface form Disambiguated ID Type / Status
Subject Have One on Me E25818 entity
Predicate hasPart P35 FINISHED
Object Kingfisher E136422 NE FINISHED

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: Kingfisher | Statement: [Have One on Me, hasPart, Kingfisher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kingfisher
Context triple: [Have One on Me, hasPart, Kingfisher]
  • A. Kingfisher chosen
    Kingfisher is a brightly colored, medium-sized bird known for its long sharp bill, excellent fishing skills, and rapid, direct flight often seen near rivers and lakes.
  • B. Pelican
    Pelican was the English galleon originally commanded by Sir Francis Drake on his circumnavigation voyage, later renamed the Golden Hind.
  • C. Ospreys
    Ospreys are a professional Welsh rugby union team based in Swansea that competes in top-level domestic and European competitions.
  • D. Osprey
    The osprey is a large fish-eating bird of prey, often called the sea hawk, known for its distinctive dark eye stripe and dramatic dives into water to catch fish.
  • E. Canary
    Canary is an experimental, bleeding-edge release channel of Google Chrome that provides the newest features and updates ahead of other versions, often at the cost of stability.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a4942b30f08190a91c60573e16b5ef completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bdbda0b081909c0147121a945e27 completed March 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac831703bc8190839deb02075cb8fd completed March 7, 2026, 7:57 p.m.
Created at: March 1, 2026, 7:46 p.m.