Triple
T19521350
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crossroads |
E488407
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Tamra 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: Tamra Davis | Statement: [Crossroads, director, Tamra Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamra Davis Context triple: [Crossroads, director, Tamra Davis]
-
A.
Tamra Davis
chosen
Tamra Davis is an American film and television director known for helming popular comedies and music videos, including the Adam Sandler movie "Billy Madison."
-
B.
Debralee Scott
Debralee Scott was an American actress best known for her comedic roles on 1970s and 1980s television sitcoms and films.
-
C.
Davina Vinyard
Davina Vinyard is a character from the film "American History X," known as the more liberal and morally grounded sister of Danny and Derek Vinyard.
-
D.
Teri Hudson
Teri Hudson is the wife of Stanley Hudson, a character from the American television series "The Office."
-
E.
Tanita Strahan
Tanita Strahan is an American visual artist and the eldest daughter of former NFL star and television personality Michael Strahan.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e635a0b37c8190b70b7427c2e85f59 |
completed | April 20, 2026, 2:18 p.m. |
Created at: April 10, 2026, 1:40 p.m.