Triple
T22546429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gloria Mildred DeHaven |
E557440
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Step Lively |
—
|
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: Step Lively | Statement: [Gloria Mildred DeHaven, notableWork, Step Lively]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Step Lively Context triple: [Gloria Mildred DeHaven, notableWork, Step Lively]
-
A.
Step Lively
chosen
Step Lively is a 1944 musical comedy film starring Frank Sinatra, known for its lighthearted plot and lively song-and-dance numbers.
-
B.
Step Off
"Step Off" is a 1984 hip hop track by Melle Mel (often credited as Grandmaster Melle Mel), known for its battle-ready lyrics and classic old-school rap style.
-
C.
Stepping Stones
Stepping Stones is a contemporary ballet choreographed by Jiří Kylián, known for its poetic exploration of memory, time, and human relationships.
-
D.
March N' Step
"March N' Step" is a track by the rapper The Peoples Champ, showcasing his Southern hip-hop style and lyrical swagger.
-
E.
Every Little Step
Every Little Step is a documentary film that chronicles the casting process and enduring legacy of the Broadway musical A Chorus Line.
- 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_69f15f35b9888190b4e1b50d5097b211 |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.