Triple
T28860107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Texas Giant |
E728835
|
entity |
| Predicate | hasManufacturerOfTrains |
P27543
|
FINISHED |
| Object | Gerstlauer |
—
|
NE NERFINISHED |
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: Gerstlauer | Statement: [New Texas Giant, hasManufacturerOfTrains, Gerstlauer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasManufacturerOfTrains Context triple: [New Texas Giant, hasManufacturerOfTrains, Gerstlauer]
-
A.
rollingStockManufacturer
chosen
Indicates that one entity is the company or organization that manufactures the rolling stock (rail vehicles) used or owned by another entity.
-
B.
hasRailwayCompanyDesign
Indicates that a railway company is responsible for the design or styling of the subject entity.
-
C.
notableTrainBrand
Indicates that an entity is a well-known or significant brand associated with trains or railway services.
-
D.
operatedLocomotiveWorksAt
Indicates that an entity operated a locomotive works facility at a specific location.
-
E.
railwayCompanyTestedOn
Indicates that a railway company has been subjected to a test, evaluation, or assessment in relation to a specified entity or context.
- 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_69f031a01cbc8190ba87270bb6fe4639 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69fee335cb08819097e3a0e09d5ebf49 |
completed | May 9, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69fee2c74fd88190acfc045ab07b7f6b |
completed | May 9, 2026, 7:31 a.m. |
Created at: April 28, 2026, 6:46 a.m.