Triple
T21652838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Ashley |
E534380
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Take Her, She’s Mine |
—
|
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: Take Her, She’s Mine | Statement: [Elizabeth Ashley, notableWork, Take Her, She’s Mine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Take Her, She’s Mine Context triple: [Elizabeth Ashley, notableWork, Take Her, She’s Mine]
-
A.
Take Her, She’s Mine
chosen
"Take Her, She’s Mine" is a 1961 stage comedy by Phoebe and Henry Ephron about an overprotective father coping with his daughter’s growing independence.
-
B.
Take Her Out
"Take Her Out" is a song by the American rock band Alice in Chains from their 2009 comeback album "Black Gives Way to Blue."
-
C.
She’s Mine, All Mine
"She’s Mine, All Mine" is a song written by American lyricist and vaudeville performer Bert Kalmar.
-
D.
I Want Her
"I Want Her" is a 1987 R&B single by Keith Sweat that became a major hit and helped define the new jack swing sound of the late 1980s.
-
E.
You’re Mine
"You’re Mine" is a song by South Korean singer-songwriter CK, known for its smooth blend of R&B and hip-hop elements.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef591594a08190bf0ddd0a0c0922ba |
completed | April 27, 2026, 12:39 p.m. |
Created at: April 16, 2026, 6:36 p.m.