Triple
T13032009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sayonara |
E326463
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Martha Scott |
E283962
|
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: Martha Scott | Statement: [Sayonara, starring, Martha Scott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martha Scott Context triple: [Sayonara, starring, Martha Scott]
-
A.
Martha Scott
chosen
Martha Scott was an American actress known for her work in film, television, and theater, including prominent roles in classic Hollywood epics.
-
B.
Martha Pattridge
Martha Pattridge is known as the wife of longtime Manhattan District Attorney Robert M. Morgenthau.
-
C.
Martha Hunt
Martha Hunt is an American fashion model best known for her work with Victoria’s Secret, including serving as a Victoria’s Secret Angel.
-
D.
Catherine Amy Dawson Scott
Catherine Amy Dawson Scott was a British novelist and playwright best known for founding PEN International, the worldwide association of writers.
-
E.
Martha McMillan Roberts
Martha McMillan Roberts was a Farm Security Administration photographer known for documenting American life during the Great Depression era.
- 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_69d8076cc45c81908123123f43e69266 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97efe72348190b52fb4068f5fb829 |
completed | April 10, 2026, 10:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff01ce8f988190b503af0cd5f2a97e |
completed | May 9, 2026, 9:43 a.m. |
Created at: April 9, 2026, 8:54 p.m.