Triple

T27515366
Position Surface form Disambiguated ID Type / Status
Subject Harold Hickory E694536 entity
Predicate provesQuality P150173 FINISHED
Object courage 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: courage | Statement: [Harold Hickory, provesQuality, courage]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: provesQuality
Context triple: [Harold Hickory, provesQuality, courage]
  • A. supportsQuality
    Indicates that one entity contributes to maintaining, enhancing, or ensuring the quality or standard of another entity or process.
  • B. hasQualityControl
    Indicates that an entity is subject to processes or measures designed to monitor, verify, and maintain the quality of its outputs or operations.
  • C. quality
    Indicates that an entity possesses a particular attribute, characteristic, or degree of excellence that defines how good, suitable, or effective it is in a given context.
  • D. qualityScheme
    Indicates that an entity is associated with a particular quality assurance or quality classification scheme that defines how its quality is evaluated or certified.
  • E. recognisedQuality chosen
    Indicates that one entity acknowledges, identifies, or validates a particular quality or attribute present in another entity.
  • F. None of above.

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_69ef53842afc8190ba6bd4e4999bda67 completed April 27, 2026, 12:16 p.m.
NER Named-entity recognition batch_69f62efbe1b48190af1b25c370672eec completed May 2, 2026, 5:06 p.m.
PD Predicate disambiguation batch_69f623aaf40081909f947431424a1d55 completed May 2, 2026, 4:17 p.m.
Created at: April 27, 2026, 1:18 p.m.