Triple
T20881879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Two Mules for Sister Sara |
E514171
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Robert F. Shugrue |
—
|
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: Robert F. Shugrue | Statement: [Two Mules for Sister Sara, editedBy, Robert F. Shugrue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert F. Shugrue Context triple: [Two Mules for Sister Sara, editedBy, Robert F. Shugrue]
-
A.
Robert F. Shugrue
chosen
Robert F. Shugrue is a film editor best known for his work on the science fiction movie "Star Trek III: The Search for Spock."
-
B.
Avery Jessup
Avery Jessup is a sharp, conservative CNBC host and Jack Donaghy’s ambitious love interest on the television series "30 Rock."
-
C.
Richard Jessup
Richard Jessup was an American novelist and screenwriter best known for writing the novel that inspired the film "The Cincinnati Kid."
-
D.
Thayer Scudder
Thayer Scudder is an American anthropologist and leading expert on the social and environmental impacts of large dam projects and resettlement programs worldwide.
-
E.
John Jay Hall
John Jay Hall is a prominent residence and dining hall building at Columbia University’s Morningside Heights campus in New York City.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67a33548190b0f5ba58b001d387 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.