Triple
T9794712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | To Serve Man |
E237689
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Susan Cummings |
E795988
|
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: Susan Cummings | Statement: [To Serve Man, castMember, Susan Cummings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Cummings Context triple: [To Serve Man, castMember, Susan Cummings]
-
A.
Susan Cummings
chosen
Susan Cummings was a German-American film and television actress active in the 1950s and 1960s, known for her roles in adventure and genre pictures as well as numerous TV guest appearances.
-
B.
Sarah Sedgwick
Sarah Sedgwick was a colonial-era New England woman known primarily as the wife of Harvard-educated lawyer and Massachusetts governor John Leverett.
-
C.
Lisa Mann
Lisa Mann is an actress known for her role in the film "Lilies of the Field."
-
D.
Lucinda Jenney
Lucinda Jenney is an American character actress known for her versatile supporting roles in films and television since the 1980s.
-
E.
Heather MacLachlan
Heather MacLachlan is best known as the wife of former U.S. Senator and diplomat George J. Mitchell.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda34916dc8190acef2ba003e56a33 |
completed | April 1, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e519c7a88190b8776b4af4908d1f |
completed | April 5, 2026, 10:41 p.m. |
Created at: March 30, 2026, 8:28 p.m.