Triple

T18592142
Position Surface form Disambiguated ID Type / Status
Subject Michael Sullivan E454393 entity
Predicate isAmbiguousIdentifier P114208 FINISHED
Object true 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: true | Statement: [Michael Sullivan, isAmbiguousIdentifier, true]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isAmbiguousIdentifier
Context triple: [Michael Sullivan, isAmbiguousIdentifier, true]
  • A. isAmbiguousName
    Indicates that a name can refer to multiple distinct entities or interpretations, making its reference unclear without additional context.
  • B. hasAmbiguous
    Indicates that the relationship or state is unclear, uncertain, or open to multiple interpretations.
  • C. hasAmbiguousIdentity chosen
    Indicates that an entity’s identity is unclear, uncertain, or can be interpreted in multiple distinct ways.
  • D. isReserved
    Indicates that something has been set aside or booked in advance for a particular person, purpose, or time, and is not available for general use.
  • E. hasAmbiguousEnding
    Indicates that the event, story, or situation concludes in a way that is open to multiple interpretations or lacks a clear, definitive resolution.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e545b6792481908eae92718aa4c889 completed April 19, 2026, 9:14 p.m.
PD Predicate disambiguation batch_69e478c98d4c81909d37a0e72c6e7bd0 completed April 19, 2026, 6:40 a.m.
Created at: April 10, 2026, 11:44 a.m.