Triple
T5473789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Blue Dahlia |
E122898
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Tom Powers |
E489062
|
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: Tom Powers | Statement: [The Blue Dahlia, starring, Tom Powers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Powers Context triple: [The Blue Dahlia, starring, Tom Powers]
-
A.
Tom Powers
chosen
Tom Powers is an actor known for his role in the film "Hellgate."
-
B.
Kemp Powers
Kemp Powers is an American playwright, screenwriter, and director best known for co-directing Pixar’s animated film "Soul" and writing the play and film "One Night in Miami."
-
C.
Joe Power
Joe Power is a British psychic medium and author known for his public demonstrations of alleged communication with the dead and related media appearances.
-
D.
Brian Rogers
Brian Rogers is a film producer best known for his work on the 2014 reboot of the Godzilla franchise.
-
E.
Laramie Eppler
Laramie Eppler is an American actor best known for his role as one of the young brothers in Terrence Malick’s acclaimed film "The Tree of Life."
- 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_69bd46459ff48190823377457bcf7128 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd9232ded08190b4142e604319b2ba |
completed | March 20, 2026, 6:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf48982b348190907c11424559cf76 |
completed | March 22, 2026, 1:40 a.m. |
Created at: March 20, 2026, 2:09 p.m.