Triple
T34505639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2.3L EcoBoost I4 (Mustang base engine) |
E885877
|
entity |
| Predicate | starter |
P20167
|
FINISHED |
| Object | electric starter |
—
|
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: electric starter | Statement: [2.3L EcoBoost I4 (Mustang base engine), starter, electric starter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starter Context triple: [2.3L EcoBoost I4 (Mustang base engine), starter, electric starter]
-
A.
starterType
chosen
Indicates the classification or category of a starter (e.g., initial component, opening item, or first phase) associated with an entity or process.
-
B.
staging
Indicates the process of arranging, organizing, or setting up elements in preparation for a main event, performance, or deployment.
-
C.
WestStarter
Indicates that an entity begins, originates, or starts from the west relative to another entity or reference point.
-
D.
startsAs
Indicates that an entity initially exists or appears in a particular form, state, or role before potentially changing to another.
-
E.
initiator
Indicates the entity that starts, triggers, or causes an action, event, or process to occur.
- 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_69f349cc0220819081f154c6964f4dc2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00383e868c819098fd17e25fcbdb04 |
completed | May 10, 2026, 7:48 a.m. |
| PD | Predicate disambiguation | batch_6a0037cc59688190b7b9da939a413db3 |
completed | May 10, 2026, 7:46 a.m. |
Created at: May 1, 2026, 2:01 a.m.