Triple
T7241973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jackie Robinson Day |
E156377
|
entity |
| Predicate | dayInYearForEvent |
P925
|
FINISHED |
| Object | April 15, 1947 |
—
|
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: April 15, 1947 | Statement: [Jackie Robinson Day, dayInYearForEvent, April 15, 1947]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dayInYearForEvent Context triple: [Jackie Robinson Day, dayInYearForEvent, April 15, 1947]
-
A.
dateDetermination
Indicates the process or criteria by which a specific date is identified, calculated, or assigned in relation to an event or condition.
-
B.
dayRelativeToEaster
Indicates the temporal offset of a given day relative to the date of Easter in a specific year (e.g., days before or after Easter Sunday).
-
C.
dateObserved
Indicates the specific date on which an event, condition, or measurement was recorded or observed.
-
D.
calendarEpoch
Indicates the reference starting point in time from which a particular calendar system counts its dates.
-
E.
notableEventDate
chosen
Indicates the date on which a notable or significant event associated with the subject occurred.
- 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_69c68827b5e481908dc05e145b2c92d4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea552a688190a00f5d0ad982f787 |
completed | March 27, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69c6e7644648819096a5e2de5d0dbe97 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:55 p.m.