Triple
T23152962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tallulah |
E578367
|
entity |
| Predicate | screenplayBy |
P15305
|
FINISHED |
| Object | Sian Heder |
—
|
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: Sian Heder | Statement: [Tallulah, screenplayBy, Sian Heder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sian Heder Context triple: [Tallulah, screenplayBy, Sian Heder]
-
A.
Sian Heder
chosen
Sian Heder is an American filmmaker and screenwriter best known for writing and directing the Academy Award–winning film "CODA."
-
B.
Sam Taylor-Johnson
Sam Taylor-Johnson is a British filmmaker and artist known for directing feature films such as "Nowhere Boy" and the adaptation of "Fifty Shades of Grey."
-
C.
Josie Rourke
Josie Rourke is a British theatre and film director known for her acclaimed stage work and for making her feature film debut with the historical drama "Mary Queen of Scots" (2018).
-
D.
Sara Haines
Sara Haines is an American television host and journalist best known as a co-host of the daytime talk show "The View" and for her work on various ABC programs.
-
E.
Joanna Vanderham
Joanna Vanderham is a Scottish actress known for her work in British television dramas and films, including prominent roles in series like "The Paradise" and "Warrior."
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efaa1fc81908fb1987dbf732f46 |
completed | April 29, 2026, 4:54 a.m. |
Created at: April 17, 2026, 4:01 p.m.