Triple
T14657974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Law of Desire |
E344157
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Carmen Maura |
E1113784
|
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: Carmen Maura | Statement: [Law of Desire, starring, Carmen Maura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carmen Maura Context triple: [Law of Desire, starring, Carmen Maura]
-
A.
Carmen Maura
chosen
Carmen Maura is a renowned Spanish actress, closely associated with director Pedro Almodóvar, celebrated for her versatile performances in both comedic and dramatic roles.
-
B.
Paz Vega
Paz Vega is a Spanish actress known for her roles in films such as "Sex and Lucía," "Spanglish," and various international productions.
-
C.
Pilar Bardem
Pilar Bardem was a Spanish actress and prominent member of the Bardem acting family, known for her extensive film and television career and her activism.
-
D.
Sara Montiel
Sara Montiel was a celebrated Spanish actress and singer who became an international film star and cultural icon in the mid-20th century.
-
E.
Josefa Ferrer
Josefa Ferrer is an actress known for playing the character Maria.
- 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb51b6a248190a44050c0e0ec2d16 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0cdc54a881909d9ea43c26b9d5ef |
completed | May 8, 2026, 4:18 p.m. |
Created at: April 10, 2026, 1:27 a.m.