Triple
T10961931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Seville |
E258995
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Dos Hermanas |
E517416
|
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: Dos Hermanas | Statement: [Port of Seville, nearbyCity, Dos Hermanas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dos Hermanas Context triple: [Port of Seville, nearbyCity, Dos Hermanas]
-
A.
Dos Hermanas
chosen
Dos Hermanas is a large suburban city in southern Spain known for its proximity to Seville and its role as an important industrial and residential center in Andalusia.
-
B.
Zamora
Zamora is a city in southern Ecuador that serves as the administrative and commercial center of Zamora-Chinchipe Province in the Amazonian foothills.
-
C.
Zamora
Zamora is a historic city in northwestern Spain known for its well-preserved Romanesque architecture and strategic location near the Portuguese border.
-
D.
Zamora
Zamora is a city in the Mexican state of Michoacán known for its agricultural production, colonial architecture, and religious landmarks such as the Cathedral of Our Lady of Guadalupe.
-
E.
Herrán
Herrán is the surname of Spanish actor Miguel Herrán, known for his roles in the series "Money Heist" and the film "A Cambio de Nada."
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7712bf65c8190b847784d885876fd |
completed | April 9, 2026, 9:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d761d3c48190af8e0aedf96ee99f |
completed | April 18, 2026, 12:59 a.m. |
Created at: April 8, 2026, 9:23 p.m.