Triple
T33898080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al-Muqtadir |
E868969
|
entity |
| Predicate | governmentDuringReign |
P87999
|
FINISHED |
| Object | Abbasid 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: Abbasid Caliphate | Statement: [Al-Muqtadir, governmentDuringReign, Abbasid Caliphate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governmentDuringReign Context triple: [Al-Muqtadir, governmentDuringReign, Abbasid Caliphate]
-
A.
heldDuringReignOf
Indicates that a role, position, or status was held by someone during the period when a particular ruler or authority was in power.
-
B.
namedDuringReignOf
Indicates that one entity received its name while another entity (typically a ruler or regime) was in power.
-
C.
functionDuringReign
Indicates that a function, role, or activity occurred or was performed during the time span of a particular ruler’s reign.
-
D.
ruledDuringReignOf
chosen
Indicates that one entity exercised ruling authority or governance during the time period in which another entity’s reign took place.
-
E.
builtDuringReignOf
Indicates that something was constructed while a particular ruler or authority was in power.
- 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_69f34997703c8190866b1d404bce531f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00bc079314819096271bba60bee52d |
completed | May 10, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_6a00bba5bd408190ace5db0c4a90dc6f |
completed | May 10, 2026, 5:08 p.m. |
Created at: May 1, 2026, 1:48 a.m.