Triple
T12426038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George P. Cosmatos |
E296899
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Leviathan |
E561654
|
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: Leviathan | Statement: [George P. Cosmatos, directed, Leviathan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leviathan Context triple: [George P. Cosmatos, directed, Leviathan]
-
A.
Leviathan
Leviathan is a clandestine, global criminal and terrorist organization in DC Comics, often depicted as a major adversary of Batman and other heroes.
-
B.
Leviathan
Leviathan is a monumental, site-specific inflatable sculpture by artist Anish Kapoor, known for its immersive, cathedral-like interior and exploration of scale, space, and perception.
-
C.
Leviathan
Leviathan is a critically acclaimed 2004 progressive/sludge metal concept album by Mastodon inspired by Herman Melville’s novel "Moby-Dick."
-
D.
Leviathan
chosen
"Leviathan" is a 1989 science fiction horror film set in an underwater mining facility, known for its creature effects and tense, claustrophobic atmosphere.
-
E.
Leviathan
"Leviathan" is a 1992 novel by Paul Auster that blends mystery, political intrigue, and metafiction as it follows a writer investigating the life and radicalization of a deceased friend.
- 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d7ccda08190be2ff1739c1c6855 |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f0265fc81909a6288d11b78c2f9 |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:55 p.m.