Triple
T22760694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don’s Party |
E562977
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Harold Hopkins |
—
|
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: Harold Hopkins | Statement: [Don’s Party, stars, Harold Hopkins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harold Hopkins Context triple: [Don’s Party, stars, Harold Hopkins]
-
A.
Harold Hopkins
chosen
Harold Hopkins was an Australian actor known for his roles in notable films and television series from the 1970s through the 1990s.
-
B.
Harold A. Hopkins
Harold A. Hopkins was an Episcopal bishop who served as the ecclesiastical leader of the Episcopal Diocese of North Dakota.
-
C.
Harold Harwood
Harold Harwood was an English screenwriter and playwright best known for his work on film and television in the mid-20th century.
-
D.
Fred Hopkins
Fred Hopkins was an influential American jazz double bassist known for his innovative work in the avant-garde and free jazz scenes, particularly with the trio Air.
-
E.
Frank Hopkins
Frank Hopkins is a legendary long-distance horse rider and cowboy whose life inspired the adventure film "Hidalgo."
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a7c45b881908b29ba1439038789 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:26 p.m.