Triple

T15767095
Position Surface form Disambiguated ID Type / Status
Subject Bonny E382249 entity
Predicate hasCapital P204 FINISHED
Object Bonny Town E1174763 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: Bonny Town | Statement: [Bonny, hasCapital, Bonny Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bonny Town
Context triple: [Bonny, hasCapital, Bonny Town]
  • A. Bonny Town chosen
    Bonny Town is a historic coastal settlement in Rivers State, Nigeria, known for its role in maritime trade and proximity to the Bonny oil and gas terminals.
  • B. Brown's Town
    Brown's Town is a historic inland market town in northern Jamaica known for its agricultural trade and vibrant local commerce.
  • C. Bodden Town
    Bodden Town is a historic coastal district and former capital on Grand Cayman in the Cayman Islands, known for its heritage sites and quiet residential character.
  • D. Port Nicholson
    Port Nicholson is the large natural harbour on the southern tip of New Zealand’s North Island that forms the setting for the city and port of Wellington.
  • E. Port Royal Cove
    Port Royal Cove is a picturesque, sheltered beach cove in Bermuda known for its calm turquoise waters and pink sand.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9099335c8190b6f0fb336b3dc212 completed May 9, 2026, 7:52 p.m.
Created at: April 10, 2026, 4:47 a.m.