Triple
T4646631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Puran Poli |
E102186
|
entity |
| Predicate | eatenDuring |
P56694
|
FINISHED |
| Object | religious festivals |
—
|
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: religious festivals | Statement: [Puran Poli, eatenDuring, religious festivals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eatenDuring Context triple: [Puran Poli, eatenDuring, religious festivals]
-
A.
eatenAs
Indicates that one entity is consumed or used as food by another entity.
-
B.
eatenOnOccasion
Indicates that one entity is consumed or eaten by another only at certain times or under specific circumstances, rather than regularly or habitually.
-
C.
isEatenIn
chosen
Indicates that one entity (typically food) is consumed within the context, location, or occasion specified by another entity.
-
D.
servedDuring
Indicates that one entity held a role, position, or performed a function within the time period defined by another entity.
-
E.
eatenInStages
Indicates that the act of eating an item occurs over multiple distinct phases or time intervals rather than in a single continuous event.
- 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_69bd43d71a308190afea7280841b0de8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd6632708c8190b627d99363ab062c |
completed | March 20, 2026, 3:22 p.m. |
| PD | Predicate disambiguation | batch_69bd620fc5e081908325ac8e6a6384ab |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:14 p.m.