Triple
T6343751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chemosh |
E142693
|
entity |
| Predicate | typeOfSacrifice |
P36512
|
FINISHED |
| Object | burnt offerings |
—
|
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: burnt offerings | Statement: [Chemosh, typeOfSacrifice, burnt offerings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSacrifice Context triple: [Chemosh, typeOfSacrifice, burnt offerings]
-
A.
sacrificeType
chosen
Indicates the specific kind or category of sacrifice involved in a sacrificial action or relationship.
-
B.
sacrifice
Indicates giving up something of value, often for the benefit, protection, or advantage of another entity or goal.
-
C.
sacrificeAnimalType
Indicates that an entity performs or is involved in the act of sacrificing an animal of a specified type.
-
D.
sacrificedTo
Indicates that one entity is offered or given up as a sacrifice in honor of, or to appease, another entity.
-
E.
viewOfSacrifices
Indicates a perspective, attitude, or evaluative stance that an entity holds toward sacrifices or acts of sacrificing.
- 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_69c008d5ab108190b346c465696824a9 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0674702d08190806ef0998960b797 |
completed | March 22, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69c060ea1a988190889e47b7e0c819b8 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:31 p.m.