Triple
T23059200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vera Caspary |
E574248
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Thelma |
—
|
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: Thelma | Statement: [Vera Caspary, wrote, Thelma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thelma Context triple: [Vera Caspary, wrote, Thelma]
-
A.
Thelma
chosen
Thelma is a feminine given name of Greek origin meaning "will" or "volition," popular in English-speaking countries during the early 20th century.
-
B.
Tideland
Tideland is a dark fantasy drama film known for its surreal, disturbing portrayal of a young girl's imagination as she copes with isolation and trauma in a desolate rural setting.
-
C.
Gothika
Gothika is a 2003 supernatural psychological horror film starring Halle Berry as a criminal psychologist who becomes a patient in her own mental institution after a mysterious, possibly paranormal incident.
-
D.
Far from Heaven
Far from Heaven is a 2002 period drama film directed by Todd Haynes that explores race, sexuality, and social norms in 1950s suburban America.
-
E.
Frida
Frida is a Swedish pop singer best known as a member of the iconic group ABBA and for her successful solo career.
- 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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1899e6c788190a2a862122cae8dc3 |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.