Triple
T29725314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chagigah (festival peace offering) |
E752162
|
entity |
| Predicate | portionBurned |
P164098
|
FINISHED |
| Object | certain fats on the altar |
—
|
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: certain fats on the altar | Statement: [Chagigah (festival peace offering), portionBurned, certain fats on the altar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portionBurned Context triple: [Chagigah (festival peace offering), portionBurned, certain fats on the altar]
-
A.
burningSince
Indicates that an object or substance has been continuously burning from a specified starting time up to the present or another reference time.
-
B.
estimatedBurnDuration
Indicates the expected length of time that something is predicted to burn or remain burning.
-
C.
remainPercentage
chosen
Indicates the proportion or percentage of something that continues to exist or is left after part of it has been used, removed, or has changed.
-
D.
burnedDownIn
Indicates that a structure or object was destroyed by fire during a particular event or incident.
-
E.
burnedDuring
Indicates that one event, object, or process was actively burning or being consumed by fire during the time span of another specified event or interval.
- 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_69f0d628c00c8190ab5ee7e423d7ec3c |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f672ff16a08190b8840351bef56f55 |
completed | May 2, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:38 p.m.