Triple
T16331351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crashing Towers |
E396559
|
entity |
| Predicate | featuresActor |
P15562
|
FINISHED |
| Object | Jack Montgomery |
E489072
|
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: Jack Montgomery | Statement: [Crashing Towers, featuresActor, Jack Montgomery]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jack Montgomery Context triple: [Crashing Towers, featuresActor, Jack Montgomery]
-
A.
Jack Montgomery
chosen
Jack Montgomery is an actor known for his role in the supernatural action film "Hellgate."
-
B.
Stan Coveleski
Stan Coveleski was a Hall of Fame Major League Baseball pitcher best known for his dominant spitball performances with the Cleveland Indians in the early 20th century.
-
C.
Austin Dempster
Austin Dempster is a cinematographer best known for his work on the fantasy-comedy film "Bedazzled."
-
D.
Jeff Reardon
Jeff Reardon is a former Major League Baseball relief pitcher who was one of the game's dominant closers in the 1980s and at one point held the all-time saves record.
-
E.
Michael Lannan
Michael Lannan is an American television writer and producer best known for creating the HBO series "Looking," which explores the lives of gay men in San Francisco.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4dfd9688190a749e48ebc055baf |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002613c0e88190b91da8eba683c864 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.