Triple
T1348336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spike Lee |
E28820
|
entity |
| Predicate | influenced |
P9
|
FINISHED |
| Object | Ryan Coogler |
E47490
|
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: Ryan Coogler | Statement: [Spike Lee, influenced, Ryan Coogler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryan Coogler Context triple: [Spike Lee, influenced, Ryan Coogler]
-
A.
Ryan Coogler
chosen
Ryan Coogler is an American filmmaker known for directing critically acclaimed films such as "Fruitvale Station," "Creed," and Marvel's "Black Panther."
-
B.
Garth Davis
Garth Davis is an Australian film and television director best known for his critically acclaimed feature "Lion" and work on the series "Top of the Lake."
-
C.
Gareth Edwards
Gareth Edwards is a Welsh former rugby union scrum-half widely regarded as one of the greatest rugby players of all time.
-
D.
Justin Lin
Justin Lin is a Taiwanese-American film director best known for revitalizing the Fast & Furious franchise and directing the science-fiction film Star Trek Beyond.
-
E.
Gavin Hood
Gavin Hood is a South African filmmaker and actor best known for directing films such as "Tsotsi," which won the Academy Award for Best Foreign Language Film, and big-budget features like "X-Men Origins: Wolverine" and "Ender's Game."
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2418e38819094683d6e1efc6e56 |
completed | March 1, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acc63c3764819094cc02e6e2332a6b |
completed | March 8, 2026, 12:43 a.m. |
Created at: March 1, 2026, 7:56 p.m.