Triple
T4761210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levite of Ephraim |
E105701
|
entity |
| Predicate | findsConcubine |
P3851
|
FINISHED |
| Object | lying at the door in the morning |
—
|
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: lying at the door in the morning | Statement: [Levite of Ephraim, findsConcubine, lying at the door in the morning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: findsConcubine Context triple: [Levite of Ephraim, findsConcubine, lying at the door in the morning]
-
A.
concubineOf
Indicates a relationship where one person is a concubine belonging to or maintained by another person.
-
B.
hasAffairWith
Indicates that one entity is engaged in a secret or illicit romantic or sexual relationship with another entity, typically outside a committed partnership.
-
C.
motherIsConcubineOf
Indicates that the person’s mother has the social or marital status of a concubine in relation to another specified individual.
-
D.
finds
chosen
Indicates that one entity discovers, locates, or comes upon another entity, often as the result of a search or encounter.
-
E.
usedAsConsortsIn
Indicates that the entities served in the role of consorts within a specified context, such as a reign, period, or relationship.
- 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_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. |
Created at: March 20, 2026, 1:20 p.m.