Triple
T35381704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | al-Mansur bi’llah Abdullah |
E1022665
|
entity |
| Predicate | confessionBranch |
P177134
|
FINISHED |
| Object | Zaydi |
—
|
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: Zaydi | Statement: [al-Mansur bi’llah Abdullah, confessionBranch, Zaydi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: confessionBranch Context triple: [al-Mansur bi’llah Abdullah, confessionBranch, Zaydi]
-
A.
confessionalBranch
chosen
Indicates that one entity is a branch, subdivision, or offshoot of another within a confessional or religious organizational structure.
-
B.
confessionObtainedBy
Indicates that a confession was acquired through a particular method, action, or process.
-
C.
confessionUse
Indicates that one entity makes use of or relies on a confession in relation to another entity or context.
-
D.
confession
Indicates that one entity admits or discloses information, typically acknowledging guilt, responsibility, or a hidden truth, to another entity.
-
E.
mainConfession
Indicates that an entity is the primary or most significant confession, admission, or acknowledgment made in relation to another entity or event.
- 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_69f76df28d8c819089f2c5799fe7d079 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
Created at: May 3, 2026, 4:03 p.m.