Triple
T16676823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M Train |
E405233
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | Tangier |
E44467
|
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: Tangier | Statement: [M Train, setting, Tangier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tangier Context triple: [M Train, setting, Tangier]
-
A.
Tangier
chosen
Tangier is a historic Moroccan port city on the Strait of Gibraltar known for its blend of North African, European, and Middle Eastern influences and its long-standing role as a cultural crossroads.
-
B.
Agadir
Agadir is a major coastal city in southwestern Morocco known for its Atlantic beaches, modern resort infrastructure, and role as a key tourist destination.
-
C.
Nador
Nador is a town in northern Algeria, likely situated within the coastal Tipaza Province west of Algiers.
-
D.
Nador
Nador is a coastal city in northeastern Morocco known as an important commercial and fishing port on the Mediterranean.
-
E.
El Aaiún
El Aaiún is the largest city and de facto administrative center of Western Sahara, located near the Atlantic coast in the disputed territory controlled by Morocco.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6b69cc8190b19632e1b4293569 |
completed | April 18, 2026, 12:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a3c79888190b6ddd55b91d97183 |
completed | May 10, 2026, 1:38 p.m. |
Created at: April 10, 2026, 5:19 a.m.