Triple
T13883556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marni Nixon |
E333777
|
entity |
| Predicate | sangFor |
P40601
|
FINISHED |
| Object | Natalie Wood |
E202322
|
NE FINISHED |
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: Natalie Wood | Statement: [Marni Nixon, sangFor, Natalie Wood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Natalie Wood Context triple: [Marni Nixon, sangFor, Natalie Wood]
-
A.
Natalie Wood
chosen
Natalie Wood was a celebrated American film and television actress known for her roles in classics such as "Rebel Without a Cause," "West Side Story," and "Splendor in the Grass."
-
B.
Madlyn Rhue
Madlyn Rhue was an American film and television actress best known for her numerous guest roles on popular series from the 1950s through the 1980s, including a memorable appearance on the original Star Trek.
-
C.
Roz Kirby
Roz Kirby was the wife of legendary comic book artist Jack Kirby and a key supporter and manager of his career.
-
D.
Lisa Dillman
Lisa Dillman is an American playwright known for her contemporary stage works and as a notable alumna of the Playwrights Workshop.
-
E.
Sue Lyon
Sue Lyon was an American actress best known for her provocative title role in Stanley Kubrick’s film "Lolita" (1962).
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d81c5dd2d48190b7a5fc1e009de936 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0bea4d248190bcbcea9ea875c5f9 |
completed | April 14, 2026, 9:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c71419b481908a3ef80abec1bf23 |
completed | May 3, 2026, 10:07 p.m. |
Created at: April 9, 2026, 10:15 p.m.