Triple
T20650531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Am the Pretty Thing That Lives in the House |
E507477
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Julie Kirkwood |
—
|
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: Julie Kirkwood | Statement: [I Am the Pretty Thing That Lives in the House, cinematographyBy, Julie Kirkwood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julie Kirkwood Context triple: [I Am the Pretty Thing That Lives in the House, cinematographyBy, Julie Kirkwood]
-
A.
Julie Kirkwood
chosen
Julie Kirkwood is a cinematographer known for her work on feature films such as the thriller "Destroyer."
-
B.
Julie Richardson
Julie Richardson is a film producer best known for her work on the acclaimed crime thriller "Collateral."
-
C.
Julie Glenn
Julie Glenn is an actress best known for her role in the French coming-of-age film "L'Effrontée."
-
D.
Julie Hagerty
Julie Hagerty is an American actress and former model best known for her comedic roles in films such as "Airplane!" and "What About Bob?".
-
E.
Julie Eldridge
Julie Eldridge is a character from the horror anthology film "Trilogy of Terror."
- 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_69e0b4bf58c081908e52a4500e03ff83 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af2133048190a6308074a3b3347e |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.