Triple
T25873701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Immortal Memory speech |
E651829
|
entity |
| Predicate | typicalDateOfOccasion |
P34404
|
FINISHED |
| Object | 25 January |
—
|
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: 25 January | Statement: [Immortal Memory speech, typicalDateOfOccasion, 25 January]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalDateOfOccasion Context triple: [Immortal Memory speech, typicalDateOfOccasion, 25 January]
-
A.
typicalDates
Indicates the usual or standard dates during which something typically occurs, is valid, or is scheduled.
-
B.
marksOccasion
Indicates that an event, action, or item serves to commemorate, celebrate, or formally recognize a particular occasion or milestone.
-
C.
typicalEventDay
chosen
Indicates the day on which an event is normally or most commonly held or occurs.
-
D.
celebratedOnOrNear
Indicates that one event, occasion, or observance is celebrated on the same date as, or within a close temporal proximity to, another.
-
E.
occasionType
Indicates the specific kind or category of occasion or event associated with the subject.
- 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_69e7ab3ad9d88190841ddcb93ab02e96 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69fddf721c1481909301a0f379368f10 |
completed | May 8, 2026, 1:04 p.m. |
| PD | Predicate disambiguation | batch_69fddda1ae7c8190b5848ff9a9e39826 |
completed | May 8, 2026, 12:57 p.m. |
Created at: April 22, 2026, 8:12 a.m.