Triple
T22721690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USNYC |
E561877
|
entity |
| Predicate | codePartLocation |
P123372
|
FINISHED |
| Object | NYC |
—
|
NE NERFINISHED |
How this triple was built (3 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: NYC | Statement: [USNYC, codePartLocation, NYC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NYC Context triple: [USNYC, codePartLocation, NYC]
-
A.
NYC
NYC is a historic American railroad company that operated major passenger and freight services across the northeastern and midwestern United States.
-
B.
New York City
chosen
New York City is the largest city in the United States, a global center of finance, culture, media, and technology.
-
C.
Manhattan
Manhattan is a village in Will County, Illinois, known as a growing suburban community southwest of Chicago.
-
D.
Manhattan
The Manhattan is a classic whiskey-based cocktail, traditionally made with rye or bourbon, sweet vermouth, and bitters, and typically served stirred and garnished with a cherry.
-
E.
Manhattan
Manhattan is the densely populated, iconic core borough of New York City, known for its skyscrapers, cultural institutions, and role as a global financial and media center.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: codePartLocation Context triple: [USNYC, codePartLocation, NYC]
-
A.
labelCodePosition
Indicates assigning a specific label to a particular position or location within a code sequence or code structure.
-
B.
documentationLocation
Indicates the place or resource where relevant documentation for an entity can be found.
-
C.
locationCodePart
chosen
Indicates that one location code is a constituent or segment of another, larger location code.
-
D.
segmentLocation
Indicates the spatial or positional relationship specifying where a particular segment is located within a larger structure or context.
-
E.
binaryLocation
Indicates that one entity is the physical or logical location where another binary or executable artifact resides.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17911a4fc81908a125209aea77e22 |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69eed2a971c0819088af574e40c9343f |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:19 p.m.