Triple
T15983635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jules-Albert de Dion |
E387635
|
entity |
| Predicate | vehicleCompetedWith |
P69210
|
FINISHED |
| Object | steam tractor with passenger trailer |
—
|
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: steam tractor with passenger trailer | Statement: [Jules-Albert de Dion, vehicleCompetedWith, steam tractor with passenger trailer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vehicleCompetedWith Context triple: [Jules-Albert de Dion, vehicleCompetedWith, steam tractor with passenger trailer]
-
A.
racedIn
Indicates that an entity participated as a competitor in a particular race or racing event.
-
B.
alsoRacedOn
chosen
Indicates that two entities participated as competitors in at least one of the same races or racing events.
-
C.
raceComponent
Indicates that one entity is a constituent part, segment, or stage within a larger race or racing event involving another entity.
-
D.
racedAs
Indicates that one entity participated in a race or competition under the identity, name, or classification of another entity.
-
E.
competedFor
Indicates that an entity took part in a contest, rivalry, or competition in pursuit of another entity (such as a prize, position, or resource).
- 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_69d86da94ccc819083d187f5dc6a123e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d9d8e881909b559a3e3ca21d24 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:54 a.m.