Triple
T19399156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States presidential inauguration |
E485270
|
entity |
| Predicate | previousStandardDate |
P34417
|
FINISHED |
| Object | March 4 |
—
|
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: March 4 | Statement: [United States presidential inauguration, previousStandardDate, March 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousStandardDate Context triple: [United States presidential inauguration, previousStandardDate, March 4]
-
A.
previousTimeStandard
Indicates that one time standard directly preceded another in chronological use or official adoption.
-
B.
formerFixedDate
chosen
Indicates that a previously established specific date associated with an event or relationship has changed and is no longer current.
-
C.
preDates
Indicates that one entity existed, occurred, or was established earlier in time than another entity.
-
D.
startDateNewStyle
Indicates the date on which something begins, expressed according to the New Style (Gregorian) calendar rather than the Old Style (Julian) calendar.
-
E.
previousPeriod
Indicates that one time period directly precedes another in a sequence of periods.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62575d78881909c2cfee799859261 |
completed | April 20, 2026, 1:09 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:36 p.m.