Triple
T9361003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Miller |
E225274
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Ronin |
E207317
|
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: Ronin | Statement: [Frank Miller, notableWork, Ronin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ronin Context triple: [Frank Miller, notableWork, Ronin]
-
A.
Ronin
chosen
Ronin is a 1998 action thriller film directed by John Frankenheimer, best known for its intricate espionage plot and realistic, high-intensity car chases set in France.
-
B.
Samurai
Samurai is a spinning thrill ride at Thorpe Park in the UK known for its intense, disorienting inversions and high-speed rotations.
-
C.
47 Ronin
47 Ronin is a 2013 fantasy action film loosely inspired by the Japanese legend of the forty-seven rōnin, blending samurai drama with supernatural elements.
-
D.
Shinya
Shinya is a Japanese given name commonly used for males.
-
E.
Ronin the Accuser
Ronin the Accuser is a Marvel Comics character associated with the cosmic side of the universe, often depicted as a powerful enforcer involved in large-scale intergalactic conflicts.
- 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_69ca842bdd648190904131d58620d448 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4ff4268c819099dd5fe79d93e7ea |
completed | April 1, 2026, 5:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0f3e27cac8190a48393fa4bdff6b8 |
completed | April 4, 2026, 11:20 a.m. |
Created at: March 30, 2026, 7:42 p.m.