Triple
T13253591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Champs-sur-Marne |
E315596
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Almada |
E177800
|
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: Almada | Statement: [Champs-sur-Marne, hasTwinTown, Almada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Almada Context triple: [Champs-sur-Marne, hasTwinTown, Almada]
-
A.
Almada
chosen
Almada is a Portuguese city located on the south bank of the Tagus River, opposite Lisbon, known for its panoramic views of the capital and its prominent Cristo Rei statue.
-
B.
Seixas
Seixas is a surname most notably associated with individuals of Portuguese and Sephardic Jewish heritage.
-
C.
Abrantes
Abrantes is a historic Portuguese city in the Santarém District, known for its hilltop castle and strategic location overlooking the Tagus River.
-
D.
Vila do Conde
Vila do Conde is a coastal city in northern Portugal known for its historic shipbuilding heritage, beaches, and well-preserved medieval architecture.
-
E.
Caldas de Reis
Caldas de Reis is a historic spa town in Galicia, northwestern Spain, known for its thermal springs and its location along 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98f7517048190b4eac4e44e81ff66 |
completed | April 11, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3237ccf88190974ff1a49c3a874b |
completed | May 8, 2026, 12:45 a.m. |
Created at: April 9, 2026, 9:24 p.m.