Triple
T20949723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batman: Assault on Arkham |
E515945
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | King Shark |
—
|
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: King Shark | Statement: [Batman: Assault on Arkham, character, King Shark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: King Shark Context triple: [Batman: Assault on Arkham, character, King Shark]
-
A.
King Shark
chosen
King Shark is a humanoid shark supervillain and occasional antihero from DC Comics, known for his immense strength, durability, and voracious appetite.
-
B.
Tigarah
Tigarah is a Japanese rapper and singer known for her eclectic blend of hip hop, baile funk, and electronic music.
-
C.
Razor the Shark
Razor the Shark is the official athletic mascot of Nova Southeastern University, representing the school's sports teams and campus spirit.
-
D.
Sharky
Sharky is a musician best known for being an early member of the British electronic music group The Prodigy.
-
E.
Mr. Shark
Mr. Shark is a comedic, disguise-loving great white shark and member of the reformed criminal crew in the animated franchise "The Bad Guys."
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fadc08148190b4ff710f94462a26 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 1:18 p.m.