Triple
T22541213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Must Love Dogs |
E557292
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Brad William Henke |
—
|
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: Brad William Henke | Statement: [Must Love Dogs, starring, Brad William Henke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad William Henke Context triple: [Must Love Dogs, starring, Brad William Henke]
-
A.
Brad William Henke
chosen
Brad William Henke was an American actor and former NFL player best known for his role as corrections officer Desi Piscatella on the television series "Orange Is the New Black."
-
B.
Evan Henke
Evan Henke is a film editor known for his work on the comedy movie "Office Christmas Party."
-
C.
Matt Hendrickson
Matt Hendrickson is a musician best known as a member of the indie rock band Low.
-
D.
Ben Wendel
Ben Wendel is a Grammy-nominated jazz saxophonist, bassoonist, composer, and bandleader known for his work with the group Kneebody and his innovative solo projects.
-
E.
Kyle Hines
Kyle Hines is an American professional basketball player renowned as one of the EuroLeague’s most successful and versatile centers, known for his defense, leadership, and multiple continental titles.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f3251808190a72b849157854d8d |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.