Triple
T7005470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Govardhan Puja |
E162442
|
entity |
| Predicate | relativeDate |
P55209
|
FINISHED |
| Object | day after the main Diwali night in many regions |
—
|
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: day after the main Diwali night in many regions | Statement: [Govardhan Puja, relativeDate, day after the main Diwali night in many regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeDate Context triple: [Govardhan Puja, relativeDate, day after the main Diwali night in many regions]
-
A.
dateRelativeTo
chosen
Indicates a temporal relationship where one date is defined, positioned, or interpreted in relation to another reference date (e.g., before, after, or offset by a specific duration).
-
B.
dateApproximate
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
C.
dateOf
Indicates that one entity specifies the calendar date associated with another entity, such as when it occurred, was created, or is scheduled.
-
D.
date
Indicates that two entities are engaged in or participate in a romantic or social outing or relationship with each other.
-
E.
reductionDate
Indicates the date on which a reduction (such as in amount, level, or status) takes effect or is officially recorded.
- 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_69c6885928148190ae31909fbb5e9849 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dc34b5a88190a793e07dd4d0018b |
completed | March 27, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c67c94819084fdcf0398606027 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:33 p.m.