Triple
T11077163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dracula (1931 film) |
E261896
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Garrett Fort |
E211619
|
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: Garrett Fort | Statement: [Dracula (1931 film), screenwriter, Garrett Fort]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Garrett Fort Context triple: [Dracula (1931 film), screenwriter, Garrett Fort]
-
A.
Garrett Fort
chosen
Garrett Fort was an American screenwriter best known for his work on classic Hollywood horror and adventure films in the 1930s and 1940s.
-
B.
Garrett Camp
Garrett Camp is a Canadian entrepreneur and investor best known as the co-founder of Uber and the founder of the discovery platform StumbleUpon.
-
C.
Hook Norton
Hook Norton is a historic Cotswold village in Oxfordshire, England, best known for its traditional Victorian tower brewery and honey-colored stone buildings.
-
D.
Garet
Garet is a given name that functions as a variant form of the name Garrett.
-
E.
Point Bennett
Point Bennett is a remote, wildlife-rich headland on the western tip of San Miguel Island in California’s Channel Islands, known for its large colonies of seals and sea lions.
- 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_69d6aa9983c08190b0ef61603b69feac |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7999407288190a901d4a2427a2102 |
completed | April 9, 2026, 12:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3c8cc77988190aad54f56dbd0f8cf |
completed | April 18, 2026, 6:09 p.m. |
Created at: April 8, 2026, 9:27 p.m.