Triple
T21205150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stanley Johnson |
E522556
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Leo 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: Leo Johnson | Statement: [Stanley Johnson, child, Leo Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Johnson Context triple: [Stanley Johnson, child, Leo Johnson]
-
A.
Leo Johnson
chosen
Leo Johnson is a British writer and sustainability expert, known for his work on business, risk, and environmental issues and as the younger brother of former UK Prime Minister Boris Johnson.
-
B.
Leo Johnson
Leo Johnson is a fictional character from the television series "Twin Peaks," known as an abusive truck driver involved in criminal activities.
-
C.
Lou Johnson
Lou Johnson was an American Major League Baseball outfielder best known for his clutch hitting with the Los Angeles Dodgers in the mid-1960s.
-
D.
Carl Johnson
Carl Johnson is an American composer best known for his work on animated television series and films, including scoring the acclaimed Disney series "Gargoyles."
-
E.
Rob Johnson
Rob Johnson is a former Rutgers University men's soccer standout recognized as a notable alumnus of the program.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734342e9081909e241bed54dbc0b4 |
completed | April 21, 2026, 8:24 a.m. |
Created at: April 16, 2026, 3:19 p.m.