Triple
T21638822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalker |
E534032
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Beth Davis |
—
|
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: Beth Davis | Statement: [Stalker, mainCharacter, Beth Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beth Davis Context triple: [Stalker, mainCharacter, Beth Davis]
-
A.
Beth Davis
chosen
Beth Davis is the lead LAPD detective specializing in stalking cases in the psychological thriller TV series "Stalker."
-
B.
Lisa Davis
Lisa Davis is a British-American actress best known for voicing Anita in Disney’s animated film "One Hundred and One Dalmatians."
-
C.
Georgia Davis
Georgia Davis was the second wife of American comedian and actor Red Skelton, with whom she shared both personal and professional aspects of his entertainment career.
-
D.
Sarah Davis
Sarah Davis was the mother of Rufus Isaacs, 1st Marquess of Reading, a prominent British lawyer, politician, and Viceroy of India.
-
E.
Emily Davis
Emily Davis is a playable character in the interactive horror video game "Until Dawn," known for her sharp wit, assertive personality, and complex relationships within the group of friends.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef538fb12481908f70ad8dbe1d99e4 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:35 p.m.