Triple
T8126552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edificio Capitol |
E189743
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Gran Vía |
E27265
|
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: Gran Vía | Statement: [Edificio Capitol, locatedOn, Gran Vía]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gran Vía Context triple: [Edificio Capitol, locatedOn, Gran Vía]
-
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.
Calle Mayor
Calle Mayor is one of Madrid’s historic main streets, linking the central Puerta del Sol with the old Habsburg quarter and the Plaza Mayor.
-
C.
Avenida de Aragón
Avenida de Aragón is a major thoroughfare in Madrid, Spain, known for connecting the city with the A-2 highway toward Zaragoza and the Madrid–Barajas Airport area.
-
D.
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.
-
E.
Calle Madrid
Calle Madrid is a street in Guadalajara, Spain, known for hosting the historic medieval tower Torreón de Álvar Fáñez.
- 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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb438eb778819085296e6cbfa2e70d |
completed | March 31, 2026, 3:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc946b44d08190a042932ee908dc2f |
completed | April 1, 2026, 3:43 a.m. |
Created at: March 30, 2026, 5:34 p.m.