Triple

T4683479
Position Surface form Disambiguated ID Type / Status
Subject Hillsborough Stadium E103859 entity
Predicate HillsboroughDisasterCause P58997 FINISHED
Object crush in overcrowded pens LITERAL 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: crush in overcrowded pens | Statement: [Hillsborough Stadium, HillsboroughDisasterCause, crush in overcrowded pens]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: HillsboroughDisasterCause
Context triple: [Hillsborough Stadium, HillsboroughDisasterCause, crush in overcrowded pens]
  • A. debatedAsCauseOf
    Indicates that one entity is discussed or argued over as a possible cause or origin of another entity.
  • B. hasCauseOfDestruction
    Indicates that one entity is the cause or agent responsible for the destruction or damage of another entity.
  • C. floodCause
    Indicates that one entity is the cause or source of a flood affecting another entity or area.
  • D. worstAccidentInSystem
    Indicates that an accident is the most severe or damaging one within a given system or context.
  • E. ceilingCollapseFatalities
    Indicates that a ceiling collapse event resulted in one or more fatalities.
  • F. None of above. chosen

Provenance (4 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_69bd43debbf08190b4bc372e286ec234 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd67c9c3c08190a6c4944cdd1362a8 completed March 20, 2026, 3:29 p.m.
PD Predicate disambiguation batch_69bd6217e0088190836570522e324dc6 completed March 20, 2026, 3:04 p.m.
PDg Predicate description generation batch_69bd67c895dc8190ba648002ff54424b completed March 20, 2026, 3:29 p.m.
Created at: March 20, 2026, 1:16 p.m.