Triple
T14332025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hispania Ulterior |
E355371
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Cordoba (Roman city) |
E37664
|
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: Cordoba (Roman city) | Statement: [Hispania Ulterior, capital, Cordoba (Roman city)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cordoba (Roman city) Context triple: [Hispania Ulterior, capital, Cordoba (Roman city)]
-
A.
Cordoba (historical)
chosen
Cordoba (historical) was a major medieval city in Al-Andalus renowned as a political, cultural, and intellectual center of the Islamic world, especially during the Umayyad Caliphate.
-
B.
Tarraconensis
Tarraconensis was a major Roman imperial province in the Iberian Peninsula, encompassing much of northern and central Spain.
-
C.
Tarraco
Tarraco was an important ancient Roman city on the Iberian Peninsula, serving as a major administrative, military, and commercial center in what is now Tarragona, Spain.
-
D.
Córdoba
Córdoba is a historic city in southern Spain renowned for its rich Moorish and medieval heritage, including the iconic Mezquita-Catedral.
-
E.
Córdoba
Córdoba is a major city in central Argentina known for its industrial base, universities, and strategic military presence.
- 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_69d8278fa2108190bc0d0e7939c1eb03 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8c1fb87c81908412c2953243c8e3 |
completed | April 14, 2026, 6:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd46943dac819092f5935d9d312949 |
completed | May 8, 2026, 2:12 a.m. |
Created at: April 10, 2026, 1:13 a.m.