Triple
T20539818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khaled Ali Abdullah Saleh |
E504296
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Saleh |
—
|
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: Saleh | Statement: [Khaled Ali Abdullah Saleh, familyName, Saleh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saleh Context triple: [Khaled Ali Abdullah Saleh, familyName, Saleh]
-
A.
Saleh
chosen
Saleh is a surname most prominently associated with Robert Saleh, the head coach of the New York Jets in the National Football League.
-
B.
Saleh Omar
Saleh Omar is a central, enigmatic refugee protagonist in Abdulrazak Gurnah’s novel "By the Sea," whose past and identity gradually unfold through his interactions and memories.
-
C.
Sa'id
Sa'id is a town in southern Yemen that historically served as the political and administrative center of the Upper Aulaqi Sultanate.
-
D.
Saleh Pat
Saleh Pat is a town located within Sukkur District in the Sindh province of Pakistan.
-
E.
Sa’id
Sa’id is a male given name of Arabic origin, commonly meaning "happy" or "fortunate."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a290bd8c819091988f511fb5820b |
completed | April 20, 2026, 10:02 p.m. |
Created at: April 16, 2026, 11:37 a.m.