Triple
T23226020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lost Dogs |
E581013
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Dirty Frank |
—
|
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: Dirty Frank | Statement: [Lost Dogs, hasPart, Dirty Frank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dirty Frank Context triple: [Lost Dogs, hasPart, Dirty Frank]
-
A.
Dirty Frank
chosen
Dirty Frank is a funk-influenced, darkly humorous Pearl Jam song known for its quirky lyrics and jam-band style experimentation.
-
B.
Totally Frank
Totally Frank is a British television drama series that follows the lives and careers of an all-girl band navigating the music industry.
-
C.
Barfly
Barfly is a 1987 semi-autobiographical drama film depicting the hard-drinking, bohemian life of a Los Angeles barfly, written by Charles Bukowski and starring Mickey Rourke and Faye Dunaway.
-
D.
Frankie and Johnny
"Frankie and Johnny" is a traditional American folk ballad about a tragic love affair that has been widely recorded and adapted across blues, jazz, and popular music.
-
E.
Freak
"Freak" is a track from Demi Lovato’s rock-influenced album "HOLY FVCK," showcasing a heavier sound and more confrontational lyrical style.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922e2d2c81908c0f3fa5df8a5c58 |
completed | April 29, 2026, 5:07 a.m. |
Created at: April 17, 2026, 4:08 p.m.