Triple
T15389330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brimstone |
E367997
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Carice van Houten |
E226238
|
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: Carice van Houten | Statement: [Brimstone, starring, Carice van Houten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carice van Houten Context triple: [Brimstone, starring, Carice van Houten]
-
A.
Carice van Houten
chosen
Carice van Houten is a Dutch actress best known internationally for her role as Melisandre in the television series "Game of Thrones."
-
B.
Ana Gasteyer
Ana Gasteyer is an American actress and comedian best known for her work on "Saturday Night Live" and roles in films and television, including the cult teen comedy "Mean Girls."
-
C.
Sylvia Hoeks
Sylvia Hoeks is a Dutch actress best known internationally for her role as the replicant Luv in the science fiction film "Blade Runner 2049."
-
D.
Annette Kurschus
Annette Kurschus is a German Protestant theologian and bishop who has served as a leading figure in the Evangelical Church in Germany.
-
E.
Taina Smits
Taina Smits is the daughter of actor Jimmy Smits and his late ex-wife Barbara Smits.
- 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e761b688190893a81246b735b76 |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff134e37d881909f373b90a99fc067 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:19 a.m.