Triple
T7763763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yemeni Air Force |
E176091
|
entity |
| Predicate | operatesAirbasesIn |
P78557
|
FINISHED |
| Object | Taiz |
E113390
|
NE 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: Taiz | Statement: [Yemeni Air Force, operatesAirbasesIn, Taiz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taiz Context triple: [Yemeni Air Force, operatesAirbasesIn, Taiz]
-
A.
Taiz
chosen
Taiz is one of Yemen’s largest and historically most important cities, known as a cultural and intellectual center in the country.
-
B.
Arafo
Arafo is a small municipality on the island of Tenerife in Spain’s Canary Islands, known for its rural landscapes and traditional Canarian character.
-
C.
Berrechid
Berrechid is a rapidly growing city in northwestern Morocco known as an important agricultural and industrial hub within the Casablanca-Settat region.
-
D.
Hamina
Hamina is a coastal town and municipality in southeastern Finland known for its historic star-shaped fortress and strategic location on the Gulf of Finland.
-
E.
Taroudant
Taroudant is a historic walled city in southern Morocco, often called the "Grandmother of Marrakech" for its similar architecture and traditional markets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c708b13c688190839c920ec196cada |
completed | March 27, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8f30ecf808190a19d57a814d45a42 |
completed | March 29, 2026, 9:38 a.m. |
Created at: March 27, 2026, 4:09 p.m.