Triple
T18419728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3 + 3 |
E441989
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | That Lady (Part 1 & 2) |
—
|
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: That Lady (Part 1 & 2) | Statement: [3 + 3, notableWork, That Lady (Part 1 & 2)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: That Lady (Part 1 & 2) Context triple: [3 + 3, notableWork, That Lady (Part 1 & 2)]
-
A.
Who’s That Lady
"Who’s That Lady" is a classic soul and R&B song by The Isley Brothers, renowned for its smooth harmonies and distinctive guitar work.
-
B.
That Lady
chosen
"That Lady" is a 1973 funk and soul hit by The Isley Brothers, known for its distinctive guitar work and smooth, psychedelic groove.
-
C.
She’s a Lady
"She’s a Lady" is a popular song written by Paul Anka that became widely known through Tom Jones’s hit 1971 recording.
-
D.
The Lady Says No
The Lady Says No is a 1951 romantic comedy film starring Joan Caulfield as a feminist author whose views on love are challenged by a brash male journalist.
-
E.
The Lady Refuses
The Lady Refuses is a 1931 American pre-Code romantic drama film directed by George Archainbaud and shot by cinematographer Joseph Walker.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a2b0f0481909c3995bf532162a3 |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 10:47 a.m.