Triple
T12002011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | al-Mahdi |
E285686
|
entity |
| Predicate | successInOffice |
P102612
|
FINISHED |
| Object | consolidated Abbasid authority over vast territories |
—
|
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: consolidated Abbasid authority over vast territories | Statement: [al-Mahdi, successInOffice, consolidated Abbasid authority over vast territories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successInOffice Context triple: [al-Mahdi, successInOffice, consolidated Abbasid authority over vast territories]
-
A.
officeSucceededBy
Indicates that one office or position is followed or replaced by another office or position in a succession sequence.
-
B.
officeSucceeded
Indicates that one office or term of office directly followed and replaced another in a sequence.
-
C.
officeWon
Indicates that a candidate successfully secured an elected office or position as the result of an election or selection process.
-
D.
succeedsFromOffice
Indicates that one officeholder directly follows another in holding the same office or position.
-
E.
officeIn
Indicates that one entity has an office located within the premises or jurisdiction of another entity.
- F. None of above. chosen
Provenance (4 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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c36b248190b446b17def94885b |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902b245cc8190af96a9c2bd9c6250 |
completed | April 10, 2026, 2:01 p.m. |
| PDg | Predicate description generation | batch_69d9038e39f881908c58c19802ba2eb0 |
completed | April 10, 2026, 2:05 p.m. |
Created at: April 8, 2026, 9:46 p.m.