Triple
T19860017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dream Brother |
E477231
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Matt 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: Matt Johnson | Statement: [Dream Brother, writer, Matt Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Johnson Context triple: [Dream Brother, writer, Matt Johnson]
-
A.
Matt Johnson
chosen
Matt Johnson is a screenwriter best known for his work on the action-thriller film "Into the Blue."
-
B.
Matthew Johnson
Matthew Johnson is a musician best known as a member of the experimental rock band Black Mountain.
-
C.
Mark Johnson
Mark Johnson is an American film and television producer best known for his work on acclaimed projects such as the series Breaking Bad.
-
D.
Mark Johnson
Mark Johnson is an American ice hockey player best known as a leading scorer and key figure in the "Miracle on Ice" U.S. team that won gold at the 1980 Winter Olympics.
-
E.
Mark Johnson
Mark Johnson is an architect best known for designing the Grand Canyon Skywalk, a glass-bottomed cantilever bridge that extends over the edge of the Grand Canyon.
- 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6586e8b648190bb650d7f2816dda1 |
completed | April 20, 2026, 4:46 p.m. |
Created at: April 10, 2026, 1:51 p.m.