Triple
T9995988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brixton Lore |
E197201
|
entity |
| Predicate | formerAllyOf |
P66534
|
FINISHED |
| Object | Deckard Shaw |
E197200
|
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: Deckard Shaw | Statement: [Brixton Lore, formerAllyOf, Deckard Shaw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deckard Shaw Context triple: [Brixton Lore, formerAllyOf, Deckard Shaw]
-
A.
Deckard Shaw
chosen
Deckard Shaw is a highly skilled former British military operative turned antihero in the Fast & Furious franchise, known for his lethal efficiency, dry wit, and complex family ties.
-
B.
Tim Quill
Tim Quill was an American actor best known for his role as Pvt. Joe Beletsky in the Vietnam War film "Hamburger Hill."
-
C.
Alexander Pierce (MCU)
Alexander Pierce (MCU) is a high-ranking S.H.I.E.L.D. official secretly serving as a key Hydra mastermind and primary antagonist in "Captain America: The Winter Soldier."
-
D.
Sam Grant
Sam Grant is a nickname for Ulysses S. Grant, the 18th president of the United States and commanding Union general during the American Civil War.
-
E.
Deckard Cain
Deckard Cain is a wise and elderly Horadric scholar from the Diablo video game series, known for identifying items and guiding heroes with his extensive knowledge of lore and demons.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcb9af6a88190942cc4991bd373c1 |
completed | April 2, 2026, 1:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d299f2a8908190a3a483350af0b5a9 |
completed | April 5, 2026, 5:20 p.m. |
Created at: March 30, 2026, 8:50 p.m.