Triple
T23481532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poseidon (2006 film) |
E570418
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Wolfgang Petersen |
—
|
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: Wolfgang Petersen | Statement: [Poseidon (2006 film), director, Wolfgang Petersen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wolfgang Petersen Context triple: [Poseidon (2006 film), director, Wolfgang Petersen]
-
A.
Wolfgang Petersen
chosen
Wolfgang Petersen was a German film director known for acclaimed works such as "Das Boot," "In the Line of Fire," and "Air Force One."
-
B.
Robert Rodat
Robert Rodat is an American screenwriter and producer best known for writing the film "Saving Private Ryan" and creating the science fiction television series "Falling Skies."
-
C.
Bob Ridley
Bob Ridley is an American soccer coach best known for managing the Dallas Tornado in the North American Soccer League.
-
D.
Michael Fleischer
Michael Fleischer is a relatively obscure individual whose primary distinguishing feature is sharing the surname associated with the Fleischer family name.
-
E.
Charles Bigelow
Charles Bigelow is an American type designer and typographic scholar best known for co-creating widely used digital fonts such as the Lucida and Wingdings families.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a75002008190b02fbffd94e5e8b1 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:03 p.m.