Triple
T22031050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gazelle Stakes |
E544085
|
entity |
| Predicate | historicalMonthRun |
P146347
|
FINISHED |
| Object | September |
—
|
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: September | Statement: [Gazelle Stakes, historicalMonthRun, September]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalMonthRun Context triple: [Gazelle Stakes, historicalMonthRun, September]
-
A.
historicalRunoffMonthBefore2015
Indicates that the referenced runoff value corresponds to a month occurring before the year 2015 in a historical time series.
-
B.
historicalBase
Indicates that one entity serves as the original or foundational source, model, or precedent upon which the other entity is historically based.
-
C.
historicalExport
Indicates that an entity was exported from one place to another during a past or historically significant period.
-
D.
historicalMethod
Indicates that a particular method, approach, or technique was used in the past, typically in a historical context or during a previous period of activity.
-
E.
hasHistoryPeriod
Indicates that something is associated with, belongs to, or occurs within a specific historical period or era.
- F. None of above. chosen
Provenance (4 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127edd5b48190a9aeb2840105c181 |
completed | April 28, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
| PDg | Predicate description generation | batch_69e6fad4a540819096cdd5ea08527220 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 8:24 p.m.