Triple
T16569155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seraphim Falls |
E402537
|
entity |
| Predicate | screenplayBy |
P15305
|
FINISHED |
| Object | Abby Everett Jaques |
E1220754
|
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: Abby Everett Jaques | Statement: [Seraphim Falls, screenplayBy, Abby Everett Jaques]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abby Everett Jaques Context triple: [Seraphim Falls, screenplayBy, Abby Everett Jaques]
-
A.
Abby Everett Jaques
chosen
Abby Everett Jaques is a screenwriter best known for her work on the 2006 American Western thriller film "Seraphim Falls."
-
B.
Abigail Mead
Abigail Mead is the pseudonym used by Vivian Kubrick, daughter of director Stanley Kubrick, under which she composed the score for the film "Full Metal Jacket."
-
C.
Abigail Lawrie
Abigail Lawrie is a Scottish actress best known for her role in the television drama series "Tin Star."
-
D.
Abigail Johnson
Abigail Johnson is an American billionaire businesswoman who serves as the CEO of Fidelity Investments, one of the largest asset management firms in the world.
-
E.
Abigail Falbury
Abigail Falbury is a fictional character portrayed by actress Gloria DeHaven, likely appearing in a mid-20th-century film or television production.
- 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_69d8838648088190acf97ef11fc3f61b |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35773c00c819091731bebc02a69bb |
completed | April 18, 2026, 10:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00759424348190889dacbbc7435238 |
completed | May 10, 2026, 12:09 p.m. |
Created at: April 10, 2026, 5:16 a.m.