Triple
T4349573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Oaks Stakes |
E97987
|
entity |
| Predicate | traditionalStartType |
P20167
|
FINISHED |
| Object | starting stalls |
—
|
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: starting stalls | Statement: [The Oaks Stakes, traditionalStartType, starting stalls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalStartType Context triple: [The Oaks Stakes, traditionalStartType, starting stalls]
-
A.
traditionalStart
Indicates that an event, process, or sequence begins in the customary or historically established way.
-
B.
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.
-
C.
traditionalEnd
Indicates that one entity is the customary or historically established conclusion, outcome, or final stage of another entity or process.
-
D.
traditionalStatus
Indicates that one entity holds a customary, long-established, or culturally recognized role, condition, or standing in relation to another entity.
-
E.
typicalStartPeriod
Indicates the usual or standard time period during which something begins or is initiated.
- 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_69b3454965f881908c41190bb22f0e4b |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351a840248190b88c8a7be9158d25 |
completed | March 12, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69b34f51ed7c8190b7bf5f44b56b730d |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:15 p.m.