Triple

T33203009
Position Surface form Disambiguated ID Type / Status
Subject Take Her to Sea, Mr. Murdoch E849954 entity
Predicate hasCueFunction P103325 FINISHED
Object underscoring ship departure 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: underscoring ship departure | Statement: [Take Her to Sea, Mr. Murdoch, hasCueFunction, underscoring ship departure]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCueFunction
Context triple: [Take Her to Sea, Mr. Murdoch, hasCueFunction, underscoring ship departure]
  • A. hasCue chosen
    Indicates that one entity provides, contains, or is associated with a signal or prompt that can guide or trigger another entity’s behavior or response.
  • B. hasScoreCue
    Indicates that one entity provides or is associated with a cue or signal used to determine, influence, or interpret the score of another entity.
  • C. hasFunctionUntil
    Indicates that an entity possesses or performs a particular function only up to a specified time or condition, after which the function no longer applies.
  • D. hasFunctionDuring
    Indicates that an entity performs or exhibits a specific function only within a specified time period or temporal context.
  • E. hasFeedbackFunction
    Indicates that one entity serves as a feedback function or mechanism associated with another entity, typically used to evaluate, adjust, or respond to that entity’s behavior or output.
  • 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_69f3495efedc8190843a5728089544b9 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69fd6a1c1c4881908090053bc359b181 completed May 8, 2026, 4:44 a.m.
PD Predicate disambiguation batch_69fd696f24d8819091033afacbdaadc5 completed May 8, 2026, 4:41 a.m.
Created at: May 1, 2026, 1:30 a.m.