Triple

T9647174
Position Surface form Disambiguated ID Type / Status
Subject Windy City E233229 entity
Predicate hasAmbiguousUse P71696 FINISHED
Object may refer to Wellington or Chicago depending on context 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: may refer to Wellington or Chicago depending on context | Statement: [Windy City, hasAmbiguousUse, may refer to Wellington or Chicago depending on context]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasAmbiguousUse
Context triple: [Windy City, hasAmbiguousUse, may refer to Wellington or Chicago depending on context]
  • A. isAmbiguousName chosen
    Indicates that a name can refer to multiple distinct entities or interpretations, making its reference unclear without additional context.
  • B. hasAmbiguousEnding
    Indicates that the event, story, or situation concludes in a way that is open to multiple interpretations or lacks a clear, definitive resolution.
  • C. hasAdjacentUse
    Indicates that one entity is used or occurs directly next to another in space, time, or sequence.
  • D. languageAmbiguity
    Indicates that the meaning, interpretation, or reference of a linguistic expression is unclear or can be understood in multiple ways.
  • E. symbolicallyUses
    Indicates that one entity employs another as a symbol or representation to convey meaning, ideas, or associations rather than for its literal or practical function.
  • 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_69ca848b31648190b57aa55da20285be completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b826ff08190a972bdef84405f08 completed April 1, 2026, 10:26 p.m.
PD Predicate disambiguation batch_69ccd5b0263081908cf6df3eb07d71b0 completed April 1, 2026, 8:22 a.m.
Created at: March 30, 2026, 8:13 p.m.