Triple
T16047371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Green |
E389257
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Amanda Green |
—
|
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: Amanda Green | Statement: [Paul Green, spouse, Amanda Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amanda Green Context triple: [Paul Green, spouse, Amanda Green]
-
A.
Amanda Green
chosen
Amanda Green is an American lyricist and composer known for her work on Broadway musicals and collaborations with prominent theater artists.
-
B.
Ash Green
Ash Green is a village in Warwickshire, England, situated within the Borough of Nuneaton and Bedworth.
-
C.
Amanda Robinson
Amanda Robinson is the spouse of Jason Robinson.
-
D.
Lindsay Greenbush
Lindsay Greenbush is an American former child actress best known for playing Carrie Ingalls on the television series "Little House on the Prairie" alongside her twin sister Sidney.
-
E.
Lauren Greene
Lauren Greene is the daughter of American politician and U.S. Representative Marjorie Taylor Greene.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1835eda348190aff492f0ff668cce |
completed | April 17, 2026, 12:48 a.m. |
Created at: April 10, 2026, 4:56 a.m.