Triple
T30626866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Fruits Festival |
E779603
|
entity |
| Predicate | typeOfFoodUsed |
P65790
|
FINISHED |
| Object | newly harvested crops |
—
|
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: newly harvested crops | Statement: [First Fruits Festival, typeOfFoodUsed, newly harvested crops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFoodUsed Context triple: [First Fruits Festival, typeOfFoodUsed, newly harvested crops]
-
A.
intendedFood
Indicates that one entity is the food item that another entity plans or is meant to eat or consume.
-
B.
isTypicallyConsumedAs
Indicates that one entity is normally or customarily eaten or drunk in the form of another entity.
-
C.
isTypicallyEatenWith
Indicates that one item is commonly consumed together with another as part of the same eating occasion or dish.
-
D.
usesFood
chosen
Indicates that one entity employs or consumes a food item as a resource, ingredient, or means to achieve some purpose.
-
E.
foodOfferedTo
Indicates that some food is presented or made available by one entity for another entity to receive or consume.
- 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_69f224a431548190a44ad9d088dbf91f |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ff7595c9bc8190982c6e6e07a0c78f |
completed | May 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69ff715432a88190a25670d26614bde2 |
completed | May 9, 2026, 5:39 p.m. |
Created at: April 29, 2026, 8:28 p.m.