Triple
T4751320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Largo do Carmo |
E105481
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Rossio |
E460963
|
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: Rossio | Statement: [Largo do Carmo, near, Rossio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rossio Context triple: [Largo do Carmo, near, Rossio]
-
A.
Rossio
chosen
Rossio is a central Lisbon square and major transport hub known for its historic architecture, lively atmosphere, and role as a key meeting point in the city.
-
B.
Glorioso
Glorioso is the traditional nickname of Brazilian football club Botafogo de Futebol e Regatas, reflecting its proud and storied history.
-
C.
Ferrera
Ferrera is a Spanish-origin surname most prominently associated with American actress and producer America Ferrera.
-
D.
Griante
Griante is a small lakeside village on Lake Como in Lombardy, Italy, known for its scenic views and historic villas.
-
E.
Rollán
Rollán is the Spanish family name of actress Maribel Verdú, known for her prominent roles in Spanish and international cinema.
- 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64c97b548190815083f2f8df907c |
completed | March 20, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43b54f548190b6118305d2a9f8d4 |
completed | March 21, 2026, 7:07 a.m. |
Created at: March 20, 2026, 1:20 p.m.