Triple

T18110800
Position Surface form Disambiguated ID Type / Status
Subject Investec Oaks E433467 entity
Predicate isRestrictedTo P126138 FINISHED
Object female horses 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: female horses | Statement: [Investec Oaks, isRestrictedTo, female horses]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isRestrictedTo
Context triple: [Investec Oaks, isRestrictedTo, female horses]
  • A. eligibilityRestrictedBy chosen
    Indicates that an entity’s eligibility for something is limited, constrained, or conditioned by another specified factor or rule.
  • B. accessRestrictedTo
    Indicates that access to a resource, location, or information is limited exclusively to a specified entity or group under defined conditions.
  • C. productionRestrictedTo
    Indicates that the production or manufacture of something is limited or confined to a specified location, entity, or set of conditions.
  • D. hasDomainRestriction
    Indicates that the relationship or property is limited to applying only to entities within a specified domain or class.
  • E. hasSemanticRestriction
    Indicates that a concept or relation is constrained in meaning or usage by specific semantic conditions or limitations.
  • 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddd2038081909515fb6d17495cbf completed April 19, 2026, 1:51 p.m.
PD Predicate disambiguation batch_69e43313ca788190baa224269e71de49 completed April 19, 2026, 1:42 a.m.
Created at: April 10, 2026, 10:28 a.m.