Triple

T4487238
Position Surface form Disambiguated ID Type / Status
Subject I'm a Celebrity...Get Me Out of Here! (UK series 5) E107271 entity
Predicate featuresCastType P56852 FINISHED
Object celebrities 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: celebrities | Statement: [I'm a Celebrity...Get Me Out of Here! (UK series 5), featuresCastType, celebrities]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: featuresCastType
Context triple: [I'm a Celebrity...Get Me Out of Here! (UK series 5), featuresCastType, celebrities]
  • A. featuresCastFrom
    Indicates that a work (such as a film or show) includes a cast member who originates from a specified source or production.
  • B. typicalCasting
    Indicates that one entity is the usual or standard casting choice for portraying another entity (such as a role, character, or type).
  • C. typicalCast
    Indicates that the associated entities form the usual or characteristic cast of characters commonly appearing in a given work or type of work.
  • D. notableCastFeature
    Indicates that a cast member has a distinctive or noteworthy characteristic, role, or attribute that is especially significant in the context of the production.
  • E. castingType
    Indicates the specific method or category of casting used to transform or represent one entity in terms of another.
  • 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_69bd43f84f788190a1383579c4a595be completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd556d29f08190bab1e872dd7e819f completed March 20, 2026, 2:10 p.m.
PD Predicate disambiguation batch_69bd5213e3d0819094b026989e686f01 completed March 20, 2026, 1:56 p.m.
PDg Predicate description generation batch_69bd556b93cc8190ab817d2817109a0b completed March 20, 2026, 2:10 p.m.
Created at: March 20, 2026, 12:59 p.m.