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.