Triple
T22671729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarazona y el Moncayo comarca |
E560233
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Ambel |
—
|
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: Ambel | Statement: [Tarazona y el Moncayo comarca, containsSettlement, Ambel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ambel Context triple: [Tarazona y el Moncayo comarca, containsSettlement, Ambel]
-
A.
Ambel
chosen
Ambel is a small municipality in the Campo de Borja comarca of the province of Zaragoza, in the autonomous community of Aragon, Spain.
-
B.
Ambezza
Ambezza is a German hip-hop producer best known for crafting beats for major international artists, including co-producing DaBaby’s hit single "ROCKSTAR."
-
C.
Amuda
Amuda is a small Kurdish-majority town in northeastern Syria, situated near the Turkish border within the al-Hasakah region.
-
D.
Ambah
Ambah is a town in the Morena district of the central Indian state of Madhya Pradesh.
-
E.
Ambelos
Ambelos is a small village on the Greek island of Gavdos, known for its remote location and traditional island character.
- 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17820a8088190bc0ce907adf95863 |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:10 p.m.