Triple
T21649026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | איזבל מלכת ישראל |
E534287
|
entity |
| Predicate | הופיעה ב |
P87363
|
FINISHED |
| Object | מלכים א' פרקים ט"ז–כ"ב |
—
|
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: מלכים א' פרקים ט"ז–כ"ב | Statement: [איזבל מלכת ישראל, הופיעה ב, מלכים א' פרקים ט"ז–כ"ב]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: הופיעה ב Context triple: [איזבל מלכת ישראל, הופיעה ב, מלכים א' פרקים ט"ז–כ"ב]
-
A.
appearedWith
Indicates that two entities were present or participated together in the same context, event, or medium.
-
B.
appearedAt
Indicates that an entity was present or made an appearance at a specific event, location, or occasion.
-
C.
appearedInEpisodeOf
chosen
Indicates that one entity made an appearance in a specific episode belonging to a television or radio series associated with the other entity.
-
D.
appearsFor
Indicates that one entity is presented, shown, or made visible on behalf of, or in representation of, another entity.
-
E.
reappearsIn
Indicates that an entity that previously appeared becomes present or visible again in the same or another context.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef59131c88819082df8e5b87f5954b |
completed | April 27, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:35 p.m.