Triple
T35302518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tinoransak |
E1019540
|
entity |
| Predicate | substitution |
P137223
|
FINISHED |
| Object | can be made with non-pork meats |
—
|
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: can be made with non-pork meats | Statement: [tinoransak, substitution, can be made with non-pork meats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: substitution Context triple: [tinoransak, substitution, can be made with non-pork meats]
-
A.
substitutionProcedure
Indicates a process in which one element, component, or entity is replaced with another according to specified rules or conditions.
-
B.
involvesSubstitute
Indicates that one entity participates in a situation, event, or role as a replacement or stand-in for another entity.
-
C.
replacement
chosen
Indicates that one entity takes the place of, or is substituted for, another entity in a given context.
-
D.
numberOfSubstitutes
Indicates the quantity of substitute entities associated with or allowed for a given entity or situation.
-
E.
sacrificeSubstituteInSomeVersions
Indicates that in some versions or variants of a narrative, ritual, or process, one entity is offered or used as a substitute sacrifice in place of another.
- 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_69f76de8b4c48190ae504b86185c474c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7904becb8819099bfe08009854ba5 |
completed | May 3, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.