Triple
T18099579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John McClane |
E433178
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Joe Leland |
—
|
NE NERFINISHED |
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: Joe Leland | Statement: [John McClane, basedOn, Joe Leland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Leland Context triple: [John McClane, basedOn, Joe Leland]
-
A.
Joe Leland
chosen
Joe Leland is a fictional former NYPD detective and the protagonist of Roderick Thorp’s thriller novel "Nothing Lasts Forever," which later inspired the film "Die Hard."
-
B.
Ed Leland
Ed Leland is a fictional American intelligence officer and love interest who works undercover in Nazi Germany in the World War II espionage drama film "Shining Through" (1992).
-
C.
Leland James
Leland James was an American businessman and entrepreneur best known as the founder of the Freightliner truck manufacturing company.
-
D.
David Leland
David Leland is a British screenwriter and director known for his gritty social dramas and collaborations with filmmaker Alan Clarke.
-
E.
Jack Lauer
Jack Lauer is the son of former "Today" show co-anchor Matt Lauer.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddb521448190b97d2b2aa7e4d7e6 |
completed | April 19, 2026, 1:50 p.m. |
Created at: April 10, 2026, 10:27 a.m.