Triple

T6921137
Position Surface form Disambiguated ID Type / Status
Subject Neque semper arcum tendit Apollo E160186 entity
Predicate negationWord P26929 FINISHED
Object neque 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: neque | Statement: [Neque semper arcum tendit Apollo, negationWord, neque]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: negationWord
Context triple: [Neque semper arcum tendit Apollo, negationWord, neque]
  • A. negates chosen
    Indicates that one entity denies, contradicts, or renders false the assertion, state, or effect expressed by another.
  • B. negativeType
    Indicates that one entity is classified as a negative, undesirable, or disfavored type in relation to another or within a given context.
  • C. negativeAcknowledgmentCharacter
    Indicates that one character responds with disagreement, refusal, or denial to another character’s statement, request, or action.
  • D. negativeFormulation
    Indicates that the associated statement, condition, or requirement is expressed in a negated or prohibitive form rather than an affirmative one.
  • E. negativePhaseAssociatedWith
    Indicates an association between something and a negative or unfavorable phase, state, or stage in a process or condition.
  • 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_69c6884d350081908d8a970e4d40ad78 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6d9fb8ac48190b50bbc47fad8288f completed March 27, 2026, 7:26 p.m.
PD Predicate disambiguation batch_69c6d7bb577c81908ee8b415b4281f3d completed March 27, 2026, 7:17 p.m.
Created at: March 27, 2026, 2:26 p.m.