Triple

T22213443
Position Surface form Disambiguated ID Type / Status
Subject Early Bird exception E549012 entity
Predicate capTreatment P147313 FINISHED
Object salary counts against cap but signing can exceed cap limit 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: salary counts against cap but signing can exceed cap limit | Statement: [Early Bird exception, capTreatment, salary counts against cap but signing can exceed cap limit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: capTreatment
Context triple: [Early Bird exception, capTreatment, salary counts against cap but signing can exceed cap limit]
  • A. caps
    Indicates that one entity serves as the capital city or administrative center of another entity, such as a country, state, or region.
  • B. coversCapital
    Indicates that one entity provides coverage, service, or applicability specifically to the capital city of another entity.
  • C. capShape
    Indicates the shape or form of the cap portion of an object in relation to its overall structure.
  • D. chapeau
    Indicates that one entity serves as a hat or head covering worn by another entity.
  • E. airCover
    Indicates the provision of protective support from the air (such as aircraft or aerial defenses) to shield or assist another force, operation, or asset.
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b2d607c81909511761b5563ddee completed April 28, 2026, 9:48 p.m.
PD Predicate disambiguation batch_69e71b4dcc408190a30429fb08fcf39e completed April 21, 2026, 6:38 a.m.
PDg Predicate description generation batch_69e723f65c5c8190a0ee3c539e5d0767 completed April 21, 2026, 7:15 a.m.
Created at: April 16, 2026, 8:37 p.m.