Triple
T35308092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abu al-Husayn Zayd ibn Ali ibn al-Husayn ibn Ali |
E1019691
|
entity |
| Predicate | revoltTarget |
P170063
|
FINISHED |
| Object | Umayyad Caliphate |
—
|
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: Umayyad Caliphate | Statement: [Abu al-Husayn Zayd ibn Ali ibn al-Husayn ibn Ali, revoltTarget, Umayyad Caliphate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: revoltTarget Context triple: [Abu al-Husayn Zayd ibn Ali ibn al-Husayn ibn Ali, revoltTarget, Umayyad Caliphate]
-
A.
oppositionTargeted
Indicates that an action or strategy is specifically directed against or aimed at an opposing party, group, or viewpoint.
-
B.
aimsToOverthrow
chosen
Indicates an intention or effort by one entity to remove another entity from power or authority, typically through forceful or subversive means.
-
C.
roleInRevolt
Indicates the specific function, position, or level of participation an entity had within a particular revolt or uprising.
-
D.
facedRebellionBy
Indicates that an entity experienced opposition or an uprising initiated by another entity.
-
E.
revoltOccurredDuring
Indicates that a revolt took place within the temporal span of a specified event or period.
- 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_69f76de8b4c48190ae504b86185c474c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f790522fbc81908a918eda08edd6e1 |
completed | May 3, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:03 p.m.