Triple
T17046437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muizz al-Dawla |
E413581
|
entity |
| Predicate | appointedCaliph |
P17619
|
FINISHED |
| Object | kept Abbasid caliph on throne as figurehead |
—
|
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: kept Abbasid caliph on throne as figurehead | Statement: [Muizz al-Dawla, appointedCaliph, kept Abbasid caliph on throne as figurehead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appointedCaliph Context triple: [Muizz al-Dawla, appointedCaliph, kept Abbasid caliph on throne as figurehead]
-
A.
proclaimedCaliphAt
Indicates that an entity was formally declared or recognized as caliph at a specific time or place.
-
B.
associatedCaliph
chosen
Indicates a relationship where an entity is linked or connected to a specific caliph, typically through rule, patronage, affiliation, or historical association.
-
C.
predecessorAsCaliph
Indicates that one entity served as the caliph immediately before another entity in a historical succession.
-
D.
servedCaliph
Indicates that one entity acted in service to, or under the authority of, a caliph.
-
E.
primaryCaliph
Indicates that one entity serves as the main or first-recognized caliph (successor/leader) in relation to another entity.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3da9e3d8881909f197aba0e4c97e7 |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.