Triple
T32756079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imam of Yemen |
E837623
|
entity |
| Predicate | penultimateTitleHolder |
P89380
|
FINISHED |
| Object | Ahmad bin Yahya |
—
|
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: Ahmad bin Yahya | Statement: [Imam of Yemen, penultimateTitleHolder, Ahmad bin Yahya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penultimateTitleHolder Context triple: [Imam of Yemen, penultimateTitleHolder, Ahmad bin Yahya]
-
A.
lastHolderTitle
Indicates the official title or position held by the most recent holder of a given role, asset, or entity.
-
B.
penultimateTo
chosen
Indicates that one entity directly precedes another in an ordered sequence, making it the second-to-last relative to that entity.
-
C.
laterTitleHolder
Indicates that one entity is a subsequent holder of a particular title or position previously held by another entity.
-
D.
titleHolderDuring
Indicates that one entity holds a specific title or position during a defined time period in relation to another entity.
-
E.
titleHeldTo
Indicates that one entity holds or possesses a specific title in relation to another entity or context.
- 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_69f34937f97c8190b7f84bea045df3ae |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:12 a.m.