Triple
T31802279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zubayrid regime |
E811772
|
entity |
| Predicate | endedWithDeathOf |
P17673
|
FINISHED |
| Object | Abd Allah ibn al-Zubayr |
—
|
NE NERFINISHED |
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: Abd Allah ibn al-Zubayr | Statement: [Zubayrid regime, endedWithDeathOf, Abd Allah ibn al-Zubayr]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endedWithDeathOf Context triple: [Zubayrid regime, endedWithDeathOf, Abd Allah ibn al-Zubayr]
-
A.
containsDeathOf
Indicates that the subject includes, depicts, or involves the death of the referenced entity.
-
B.
afterDeathOf
Indicates that one event, state, or condition occurs subsequent to and as a result of the death of a specified entity.
-
C.
completionAfterDeathOf
Indicates that one event, process, or work is completed only after the death of a specified person.
-
D.
continuedAfterDeathOf
Indicates that an action, state, or process persisted beyond and despite the death of a specified entity.
-
E.
associatedWithDeathOf
chosen
Indicates a relationship where one entity is connected in some relevant way to the death of another entity, such as by involvement, causation, or contextual association.
- 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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:42 p.m.