Triple
T21461069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cines Callao |
E529472
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Gran Vía, Madrid |
—
|
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: Gran Vía, Madrid | Statement: [Cines Callao, locatedNear, Gran Vía, Madrid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gran Vía, Madrid Context triple: [Cines Callao, locatedNear, Gran Vía, Madrid]
-
A.
Gran Vía
chosen
Gran Vía is one of Madrid’s most famous and bustling avenues, known for its grand architecture, theaters, shops, and vibrant nightlife.
-
B.
Gran Vía
Gran Vía is a major thoroughfare in Zaragoza, Spain, known for its central location, commercial activity, and role as a key public transport corridor.
-
C.
Calle de Madrid
Calle de Madrid is a historic street in central Madrid, Spain, located near the Plaza de la Villa in the city’s old quarter.
-
D.
Calle Madrid
Calle Madrid is a street in Guadalajara, Spain, known for hosting the historic medieval tower Torreón de Álvar Fáñez.
-
E.
Calle del Prado
Calle del Prado is a historic street in central Madrid, Spain, known for its proximity to major cultural landmarks such as the Prado Museum and the city’s literary quarter.
- 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9ee10ec8190a606aa64001af35e |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:09 p.m.