Triple
T18878017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wilmerding, Pennsylvania |
E461737
|
entity |
| Predicate | hasIndustryHistoric |
P3008
|
FINISHED |
| Object | railroad air brake 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: railroad air brake manufacturing | Statement: [Wilmerding, Pennsylvania, hasIndustryHistoric, railroad air brake manufacturing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIndustryHistoric Context triple: [Wilmerding, Pennsylvania, hasIndustryHistoric, railroad air brake 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.
hasIndustrialHeritage
Indicates that an entity possesses or is associated with historically significant industrial sites, structures, or practices.
-
C.
hasBusinessHeritage
Indicates that an entity possesses a historical or traditional connection to a particular business, company, or commercial lineage.
-
D.
hadStateOwnershipOfIndustry
Indicates that a governing authority or state entity possessed ownership and control over a particular industry.
-
E.
hasHistoricalCategory
Indicates that something is associated with a particular historical classification, period, or type based on its past context or significance.
- 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c3cfc4408190a7ae91459f75be52 |
completed | April 20, 2026, 6:12 a.m. |
| PD | Predicate disambiguation | batch_69e48d22dde8819093b1d963bd673365 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:57 a.m.