Triple

T11445882
Position Surface form Disambiguated ID Type / Status
Subject Rassie Erasmus E271261 entity
Predicate playedForTeam P2168 FINISHED
Object Golden Lions E453811 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: Golden Lions | Statement: [Rassie Erasmus, playedForTeam, Golden Lions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Golden Lions
Context triple: [Rassie Erasmus, playedForTeam, Golden Lions]
  • A. Golden Lions
    The Golden Lions are the top prizes awarded for best film at Poland’s prestigious Gdynia Film Festival.
  • B. Golden Lions chosen
    The Golden Lions are a professional South African rugby union team based in Johannesburg that competes in domestic and international competitions.
  • C. Golden Bulls
    Golden Bulls is the athletic mascot and nickname representing the sports teams of Johnson C. Smith University.
  • D. The Lions
    The Lions is the nickname of Millwall F.C., a professional football club based in South East London known for its passionate fanbase and long-standing presence in English football.
  • E. The Lions
    The Lions is the nickname of Livingston F.C., a professional football club based in Livingston, Scotland.
  • 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_69d6aadff8888190a13f253f0d460874 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8088a66f48190b2b4a56cd62097cf completed April 9, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d3afe7fc8190acc8c803ff5efe5a completed April 20, 2026, 7:20 a.m.
Created at: April 8, 2026, 9:35 p.m.