Triple
T11993922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moroccan Sahara |
E285479
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Zagora |
E307873
|
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: Zagora | Statement: [Moroccan Sahara, hasTown, Zagora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zagora Context triple: [Moroccan Sahara, hasTown, Zagora]
-
A.
Zagora
chosen
Zagora is a town in southeastern Morocco that serves as a gateway to the Sahara Desert and popular nearby dune fields.
-
B.
Zagora
Zagora is a traditional mountain village in eastern Pelion, Greece, known for its stone-built houses, rich history, and views over the Aegean Sea.
-
C.
El Ejido
El Ejido is a major agricultural town in southeastern Spain, renowned for its extensive greenhouse farming and intensive fruit and vegetable production.
-
D.
Guadix
Guadix is a historic Andalusian town in southern Spain, noted for its cave dwellings and impressive cathedral set against the Sierra Nevada foothills.
-
E.
Tetuan
Tetuan is a Barcelona Metro station on line 2 located beneath Plaça de Tetuan in the Eixample district of Barcelona, Spain.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903b211688190bfe6dd15c3f96d2f |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f48ad06350819094180403858db172 |
completed | May 1, 2026, 11:13 a.m. |
Created at: April 8, 2026, 9:46 p.m.