Triple
T4852560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abner |
E108449
|
entity |
| Predicate | promisedTo |
P10010
|
FINISHED |
| Object | bring all Israel to David |
—
|
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: bring all Israel to David | Statement: [Abner, promisedTo, bring all Israel to David]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promisedTo Context triple: [Abner, promisedTo, bring all Israel to David]
-
A.
promises
chosen
Indicates that one entity commits to performing, providing, or ensuring something for another entity in the future.
-
B.
pledgedByOthers
Indicates that a commitment, promise, or pledge toward an entity is made by parties other than the primary or focal entity.
-
C.
confirmedFor
Indicates that an entity has been officially approved, scheduled, or validated to participate in, receive, or be associated with another specified entity or event.
-
D.
promiseOfBlessingTo
Indicates that one entity has declared or assured a future blessing or favorable outcome to another entity.
-
E.
committed
Indicates that an agent has carried out or been responsible for a specific act, event, or wrongdoing.
- 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_69bd440a89548190a5f14ba6da6b97dc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddd17d881909f7731ff2b460e83 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2557388190a2d15571bacd24f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:26 p.m.