Triple
T15614930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madrid–Andalusia railway |
E375387
|
entity |
| Predicate | startPoint |
P389
|
FINISHED |
| Object | Madrid |
E4617
|
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: Madrid | Statement: [Madrid–Andalusia railway, startPoint, Madrid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madrid Context triple: [Madrid–Andalusia railway, startPoint, Madrid]
-
A.
Madrid
Madrid is a municipality in the Cundinamarca department of Colombia, located near Bogotá and known for its floriculture and agricultural production.
-
B.
Madrid
Madrid is a coastal municipality in the Philippine province of Surigao del Sur on the island of Mindanao.
-
C.
Madrid
chosen
Madrid is the capital and largest city of Spain, renowned for its rich cultural heritage, historic architecture, and vibrant arts and nightlife scenes.
-
D.
Madri
Madri is a princess from the Mahabharata epic, known as the second wife of King Pandu and the mother of the twins Nakula and Sahadeva.
-
E.
Seville
Seville is a historic Spanish city in Andalusia renowned for its rich Moorish and Christian heritage, iconic landmarks like the Giralda and Alcázar, and vibrant cultural traditions such as flamenco.
- 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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e83407c8190abbcd4b7fab0ff85 |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff678a9fac81908030726054ff5a99 |
completed | May 9, 2026, 4:57 p.m. |
Created at: April 10, 2026, 4:13 a.m.