Triple
T2049871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Galicia |
E45539
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Ourense |
E202011
|
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: Ourense | Statement: [Kingdom of Galicia, hasCity, Ourense]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ourense Context triple: [Kingdom of Galicia, hasCity, Ourense]
-
A.
Ourense
chosen
Ourense is a historic inland city in northwestern Spain known for its thermal springs and Roman bridge over the Miño River.
-
B.
A Coruña
A Coruña is a coastal city in northwestern Spain known for its historic lighthouse, the Tower of Hercules, and its role as an important cultural and economic center in the region.
-
C.
Pontevedra
Pontevedra is a coastal province in northwestern Spain known for its historic towns, Atlantic landscapes, and location within the autonomous community of Galicia.
-
D.
Ferrol
Ferrol is a coastal city and major naval shipbuilding center in the Galicia region of northwestern Spain.
-
E.
Logroño
Logroño is the capital city of Spain’s La Rioja region, renowned for its historic old town, vibrant tapas culture, and role as a key stop on the Camino de Santiago pilgrimage route.
- 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_69a8891948208190ab7898da21824c77 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb98e10d48190bb96cd1f8ea3c08b |
completed | March 7, 2026, 5:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58c2cb688190ae3320bbf4e0dfa9 |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:39 p.m.