Triple
T5727780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Worthington |
E126306
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Rogue |
E542200
|
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: Rogue | Statement: [Sam Worthington, appearedIn, Rogue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rogue Context triple: [Sam Worthington, appearedIn, Rogue]
-
A.
Rogue
Rogue is a popular Marvel Comics superhero and member of the X-Men known for her ability to absorb others’ powers and memories through touch.
-
B.
Rogue
Rogue is a Hearthstone class focused on stealth, combo-based gameplay, and efficient removal using daggers, spells, and sneaky minions.
-
C.
Rogue
chosen
Rogue is a 2007 Australian horror thriller film about tourists trapped by a giant man-eating crocodile in a remote Northern Territory river.
-
D.
Renegade
"Renegade" is a standout hip-hop track best known for featuring Eminem alongside Jay-Z, where both deliver intricate, hard-hitting verses over a dark, minimalist beat.
-
E.
Havoc
Havoc is an American rapper and record producer best known as one half of the influential hip-hop duo Mobb Deep.
- 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_69c0082f723881908ce8bb13a0c0f8b7 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0250c0ca081909340abae204cc226 |
completed | March 22, 2026, 5:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07dffe45481909eb617e40c83bd14 |
completed | March 22, 2026, 11:40 p.m. |
Created at: March 22, 2026, 3:47 p.m.