Triple
T4761212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levite of Ephraim |
E105701
|
entity |
| Predicate | cutsBodyOfConcubine |
P58378
|
FINISHED |
| Object | into twelve pieces |
—
|
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: into twelve pieces | Statement: [Levite of Ephraim, cutsBodyOfConcubine, into twelve pieces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cutsBodyOfConcubine Context triple: [Levite of Ephraim, cutsBodyOfConcubine, into twelve pieces]
-
A.
concubineOf
Indicates a relationship where one person is a concubine belonging to or maintained by another person.
-
B.
coneSex
Indicates a sexual or mating relationship involving a cone-shaped structure or entity.
-
C.
motherIsConcubineOf
Indicates that the person’s mother has the social or marital status of a concubine in relation to another specified individual.
-
D.
castrated
Indicates that an entity has undergone a procedure to remove or inactivate its reproductive organs, thereby preventing it from reproducing.
-
E.
abolishesBody
Indicates that one entity formally ends, eliminates, or does away with another entity or institutional body.
- F. None of above. chosen
Provenance (4 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_69bd43f14cac819081c7c69803648211 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd650eefe08190b99f9f01b121dbfd |
completed | March 20, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69bd6225c9488190afee5bb3619d0365 |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd631328fc81909b28ae0a2a3ed9bb |
completed | March 20, 2026, 3:09 p.m. |
Created at: March 20, 2026, 1:20 p.m.