Triple
T19270705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southwest Yonkers |
E481914
|
entity |
| Predicate | historicallyHadIndustryType |
P3008
|
FINISHED |
| Object | manufacturing |
—
|
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: manufacturing | Statement: [Southwest Yonkers, historicallyHadIndustryType, manufacturing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyHadIndustryType Context triple: [Southwest Yonkers, historicallyHadIndustryType, manufacturing]
-
A.
hasHistoricIndustry
chosen
Indicates that an entity has been associated with a notable or historically significant industry or industrial activity in the past.
-
B.
hadStateOwnershipOfIndustry
Indicates that a governing authority or state entity possessed ownership and control over a particular industry.
-
C.
hasIndustrialSector
Indicates that an entity is associated with, operates in, or belongs to a particular industrial sector or branch of economic activity.
-
D.
hasHistoricalOccupationMaterial
Indicates that something is composed of or contains material evidence related to past occupations or uses by people.
-
E.
hasFoundingIndustryAssociation
Indicates that an entity is associated with an industry organization that played a role in its founding or establishment.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbb8bea08190b5c65eebe67dccbb |
completed | April 20, 2026, 10:11 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:29 p.m.