Triple
T23123391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Harroun |
E576959
|
entity |
| Predicate | dateOfEventWin |
P45877
|
FINISHED |
| Object | 1911-05-30 |
—
|
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: 1911-05-30 | Statement: [Ray Harroun, dateOfEventWin, 1911-05-30]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfEventWin Context triple: [Ray Harroun, dateOfEventWin, 1911-05-30]
-
A.
capitalEventDate
Indicates the date on which a capital-related event (such as establishment, designation, or change of capital status) occurred.
-
B.
dateOfVictory
chosen
Indicates the specific calendar date on which a victory or winning outcome occurred.
-
C.
eventDateContext
Indicates the contextual role or significance that a specific date has within an event (e.g., whether it is the start, end, deadline, or another relevant temporal marker).
-
D.
eventDateJudged
Indicates that a specific date has been evaluated or determined in relation to an event (e.g., as its official or relevant date).
-
E.
mainEventDate
Indicates the primary or most significant date on which the referenced event occurs or is scheduled 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e517a0481909829a73fdf255d1c |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.