Triple
T7595195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flash Gordon |
E179840
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Topol |
E675158
|
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: Topol | Statement: [Flash Gordon, starring, Topol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Topol Context triple: [Flash Gordon, starring, Topol]
-
A.
Topol
chosen
Topol was an Israeli actor and singer best known internationally for his iconic portrayal of Tevye in the film adaptation of the musical "Fiddler on the Roof."
-
B.
Tom Topor
Tom Topor is an American screenwriter and playwright best known for his work on the acclaimed courtroom drama film "The Accused."
-
C.
Kloves
Kloves is the surname of American screenwriter and film director Steve Kloves, best known for adapting most of the Harry Potter novels for the screen.
-
D.
Boris Kodjoe
Boris Kodjoe is a German-born Austrian actor and former fashion model best known for his roles in film and television series such as "Soul Food" and "Station 19."
-
E.
Peter Facinelli
Peter Facinelli is an American actor best known for playing Dr. Carlisle Cullen in the Twilight film series.
- 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_69c69f3487ec8190bf7acdf2dd91e6d6 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f9bbcd8081909a229d7faa2ffdc8 |
completed | March 27, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c86843a7808190a4c1d3c33a7441ed |
completed | March 28, 2026, 11:46 p.m. |
Created at: March 27, 2026, 3:53 p.m.