Triple
T20620604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flicka |
E506687
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Dallas Roberts |
—
|
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: Dallas Roberts | Statement: [Flicka, starring, Dallas Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dallas Roberts Context triple: [Flicka, starring, Dallas Roberts]
-
A.
Dallas Roberts
chosen
Dallas Roberts is an American actor known for his versatile roles in film, television, and theater, including appearances in projects like "Dallas Buyers Club" and the series "The Walking Dead."
-
B.
Glenn Roberts
Glenn Roberts is an American grain expert and founder of Anson Mills, renowned for reviving heirloom Southern grains and rice varieties, including Carolina Gold rice.
-
C.
Davis Roberts
Davis Roberts was an American character actor known for his numerous supporting roles in film and television from the 1950s through the 1980s.
-
D.
Ken Rogerson
Ken Rogerson is a film editor known for his work on the animated dark fantasy film "Mad God."
-
E.
Larry Robinson
Larry Robinson is an actor best known for his role on the television sitcom "The Goldbergs."
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe19ca481908c896bec49a025cd |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.