Triple
T20957407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duquesne Whistle |
E516136
|
entity |
| Predicate | featuresImagery |
P17123
|
FINISHED |
| Object | trains |
—
|
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: trains | Statement: [Duquesne Whistle, featuresImagery, trains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresImagery Context triple: [Duquesne Whistle, featuresImagery, trains]
-
A.
usesImagery
Indicates that one entity employs descriptive or figurative language to create sensory or vivid mental images in relation to another entity or concept.
-
B.
hasImageryFrom
Indicates that one entity contains, incorporates, or is derived from the imagery produced or provided by another entity.
-
C.
hasColorImagery
Indicates that something includes or is characterized by visual elements emphasizing specific colors or color-based symbolism.
-
D.
sceneFeature
Indicates a characteristic, element, or attribute that is present within or helps define a particular scene.
-
E.
usesImageryOf
chosen
Indicates that one entity employs or incorporates visual or sensory imagery that depicts, references, or symbolically represents another entity.
- 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_69e0b4fde6c48190af1398e7e734629e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fb6c2f1481908360fb86d2b6a8e4 |
completed | April 21, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69e5c9b1bae48190a845165fed1b005e |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 1:28 p.m.