Triple
T8156036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Underworld |
E190451
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object | Kraven |
E703868
|
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: Kraven | Statement: [Underworld, notableCharacter, Kraven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kraven Context triple: [Underworld, notableCharacter, Kraven]
-
A.
Kraven the Hunter
chosen
Kraven the Hunter is a Marvel Comics supervillain and Spider-Man adversary, known as a master big-game hunter obsessed with proving himself as the world’s greatest predator.
-
B.
Skerik
Skerik is an American saxophonist known for his experimental, jazz, and rock collaborations, particularly in the Seattle music scene.
-
C.
Green Goblin
Green Goblin is one of Spider-Man’s most iconic arch-enemies, a deranged, high-tech villain known for his glider, pumpkin bombs, and split personality.
-
D.
Mr. Kane
Mr. Kane is a hip-hop artist who contributed a guest appearance to Snoop Dogg’s album "Paid tha Cost to Be da Boss."
-
E.
Mr. Kane
Mr. Kane is the husband of Mary Kane, a character associated with the backstory of Charles Foster Kane in the classic film "Citizen Kane."
- 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_69ca82bfeb6481909d07b91b5cf69f59 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb44d8a37481909397b5cc321b94be |
completed | March 31, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf0f68c88190be9aab03de6bf4a0 |
completed | April 1, 2026, 6:45 a.m. |
Created at: March 30, 2026, 5:37 p.m.