Triple

T38489990
Position Surface form Disambiguated ID Type / Status
Subject Homer (Near Dark) E918027 entity
Predicate bodyAgeDescription P190956 FINISHED
Object eternally childlike 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: eternally childlike | Statement: [Homer (Near Dark), bodyAgeDescription, eternally childlike]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: bodyAgeDescription
Context triple: [Homer (Near Dark), bodyAgeDescription, eternally childlike]
  • A. typicalAgingPotentialRange
    Indicates the usual range of time over which something is expected to age or mature under normal conditions.
  • B. containsAge
    Indicates that one entity includes or specifies the age value or age-related information of another entity.
  • C. ageType
    Indicates the specific categorization or classification of an age value (e.g., actual, estimated, range-based) associated with an entity.
  • D. ageDetail
    Indicates a detailed specification of an entity’s age, such as exact value, range, or related age attributes.
  • E. ageStatus
    Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
  • 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_69f76e9894208190a129a553a60ca58c completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fcd34596288190b8e34a7a20b4c0db completed May 7, 2026, 6 p.m.
PD Predicate disambiguation batch_69fcd1f6b2e08190bf0300ae7c9ae67a completed May 7, 2026, 5:55 p.m.
PDg Predicate description generation batch_69fcd31227708190a7df213597e66ca8 completed May 7, 2026, 5:59 p.m.
Created at: May 3, 2026, 4:31 p.m.