Triple
T8628251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aquaman and the Lost Kingdom |
E204332
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Arthur Curry |
E195743
|
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: Arthur Curry | Statement: [Aquaman and the Lost Kingdom, mainCharacter, Arthur Curry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arthur Curry Context triple: [Aquaman and the Lost Kingdom, mainCharacter, Arthur Curry]
-
A.
Arthur Curry
chosen
Arthur Curry is the human-Atlantean superhero better known as Aquaman, king of Atlantis and a founding member of the Justice League in DC Comics.
-
B.
Oliver Queen
Oliver Queen is a billionaire playboy-turned-vigilante archer who fights crime as the Green Arrow in DC Comics and its television adaptations.
-
C.
Black Manta
Black Manta is a vengeful, high-tech mercenary and one of Aquaman’s most iconic archenemies in DC Comics.
-
D.
Owen Harper
Owen Harper is a central character in the British sci-fi series "Torchwood," serving as the team's acerbic and brilliant medical officer.
-
E.
Sam Holland
Sam Holland is a British actor and social media personality best known as one of Tom Holland’s younger brothers and for appearing in some of his projects and online content.
- 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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc472ccc0c81908e0708c94a7cbe65 |
completed | March 31, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cecc9abd1081909d45af7498ec7c34 |
completed | April 2, 2026, 8:07 p.m. |
Created at: March 30, 2026, 6:27 p.m.