Triple

T8487607
Position Surface form Disambiguated ID Type / Status
Subject FC Dordrecht E200868 entity
Predicate shortName P43 FINISHED
Object FC Dordrecht E200868 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: FC Dordrecht | Statement: [FC Dordrecht, shortName, FC Dordrecht]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FC Dordrecht
Context triple: [FC Dordrecht, shortName, FC Dordrecht]
  • A. FC Dordrecht chosen
    FC Dordrecht is a professional Dutch football club based in Dordrecht that competes in the country's league system, traditionally in the Eerste Divisie.
  • B. FC Utrecht
    FC Utrecht is a professional Dutch football club based in Utrecht that competes in the Eredivisie and is regarded as one of the country’s prominent teams.
  • C. FC Eindhoven
    FC Eindhoven is a Dutch professional football club from Eindhoven that competes in the country’s league system and shares a historic city rivalry with PSV Eindhoven.
  • D. SC Heerenveen
    SC Heerenveen is a Dutch professional football club based in Heerenveen, known for competing in the Eredivisie and developing young talent.
  • E. FC Twente
    FC Twente is a professional football club from Enschede in the Netherlands, known for competing in the Eredivisie and winning the Dutch league title in 2010.
  • 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_69ca831d7b148190a6e32c1de43ab13b completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe556b5188190b1124effd7445803 completed March 31, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4df197c48190812c5287119e5528 completed April 2, 2026, 11:07 a.m.
Created at: March 30, 2026, 6:13 p.m.