Triple
T10920120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thaddeus Ross |
E257924
|
entity |
| Predicate | conflictWith |
P4897
|
FINISHED |
| Object | Bruce Banner |
E210062
|
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: Bruce Banner | Statement: [Thaddeus Ross, conflictWith, Bruce Banner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bruce Banner Context triple: [Thaddeus Ross, conflictWith, Bruce Banner]
-
A.
Bruce Banner
chosen
Bruce Banner is a brilliant scientist who transforms into the powerful Hulk, serving as a key member of the Avengers in the Marvel universe.
-
B.
Hulk
Hulk is a powerful Brazilian professional footballer known for his explosive strength, long-range shooting, and successful stints in European and Asian clubs.
-
C.
Max Dillon
Max Dillon is a Marvel Comics character who becomes the electricity-manipulating supervillain Electro and serves as one of Spider-Man’s primary adversaries.
-
D.
Hulkling (Teddy Altman)
Hulkling (Teddy Altman) is a Marvel Comics superhero, a shape-shifting Kree–Skrull hybrid best known as a founding member of the Young Avengers and the romantic partner of Wiccan.
-
E.
Steven Rogers
Steven Rogers is an American screenwriter known for writing character-driven dramas and comedies, including the film "Hope Floats."
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77081a0c48190b7aa4a482032d1ea |
completed | April 9, 2026, 9:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2171adbbc8190916a5463b6e5c186 |
completed | April 17, 2026, 11:18 a.m. |
Created at: April 8, 2026, 9:22 p.m.