Triple
T20744152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter’s Friends |
E510525
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Hugh Laurie |
—
|
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: Hugh Laurie | Statement: [Peter’s Friends, starring, Hugh Laurie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hugh Laurie Context triple: [Peter’s Friends, starring, Hugh Laurie]
-
A.
Hugh Laurie
chosen
Hugh Laurie is an English actor, comedian, musician, and writer best known internationally for his role as Dr. Gregory House in the television series "House."
-
B.
David Harewood
David Harewood is a British actor known for his work in television series such as "Homeland" and "Supergirl" as well as numerous film and stage roles.
-
C.
Jared Harris
Jared Harris is a British actor known for his character roles in film and television, including acclaimed performances in series like "Mad Men," "Chernobyl," and "The Crown."
-
D.
Michael York
Michael York is an English actor known for his roles in films such as "Cabaret," "Logan's Run," and the "Austin Powers" series.
-
E.
Patrick J. Sullivan
Patrick J. Sullivan was a notable individual interred at Mount Olivet Cemetery in Washington, D.C., recognized for his significance to the local community or broader historical record.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c21197088190951a4c4a7e765891 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:33 p.m.