Triple
T18834376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antoni Tàpies |
E460618
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Teresa Barba |
—
|
NE NERFINISHED |
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: Teresa Barba | Statement: [Antoni Tàpies, spouse, Teresa Barba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Teresa Barba Context triple: [Antoni Tàpies, spouse, Teresa Barba]
-
A.
Teresa Barba
chosen
Teresa Barba was the wife and close companion of renowned Catalan painter and sculptor Antoni Tàpies.
-
B.
Teresa Borri
Teresa Borri was the second wife of Italian novelist and poet Alessandro Manzoni, known primarily for her association with the celebrated author of "The Betrothed."
-
C.
Teresa Pomar
Teresa Pomar was a prominent Mexican researcher, curator, and promoter of folk and popular art, recognized for her extensive work preserving and documenting Mexico’s artisanal traditions.
-
D.
Teresa Viola
Teresa Viola is an American businesswoman and philanthropist known for her involvement in charitable initiatives and as the wife of billionaire businessman and NHL team owner Vincent Viola.
-
E.
Pilar Castro
Pilar Castro is a Spanish actress known for her work in film, television, and theater.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99c1394819095c62eef040e552c |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.