Triple
T20619935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Mummy (2017 film) |
E506671
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jake Johnson |
—
|
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: Jake Johnson | Statement: [The Mummy (2017 film), starring, Jake Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jake Johnson Context triple: [The Mummy (2017 film), starring, Jake Johnson]
-
A.
Jake Johnson
Jake Johnson is the son of Brad Johnson.
-
B.
Jake Johnson
chosen
Jake Johnson is an American actor and comedian best known for his role on the TV series "New Girl" and for voicing Peter B. Parker in the animated film "Spider-Man: Into the Spider-Verse."
-
C.
Tor Johnson
Tor Johnson was a Swedish-born professional wrestler and character actor best known for his roles in low-budget 1950s horror and science fiction films, particularly those directed by Ed Wood.
-
D.
Connor Johnson
Connor Johnson is a professional basketball coach recognized as the NBA G League Coach of the Year for the 2020–21 season.
-
E.
Dylan Johnson
Dylan Johnson is a member of the Johnson & Johnson family, associated with the legacy behind the multinational healthcare and consumer goods corporation.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe0e22c81909f6efe21518e33f0 |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:41 a.m.