Triple
T12685809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Brown |
E303062
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Sarah Curtis |
E161293
|
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: Sarah Curtis | Statement: [Mrs Brown, producer, Sarah Curtis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Curtis Context triple: [Mrs Brown, producer, Sarah Curtis]
-
A.
Sarah Curtis
chosen
Sarah Curtis is a British film producer known for her work on acclaimed dramas and literary adaptations, including the World War II film "Charlotte Gray."
-
B.
Amelia Curtis
Amelia Curtis is a British actress known for her work in film and television, including roles in series such as "Lovejoy" and "The Bill."
-
C.
Mary Crosby
Mary Crosby is an American actress best known for her role as Kristin Shepard on the television series "Dallas."
-
D.
Maria Cooley
Maria Cooley was the wife of American landscape painter Jasper Francis Cropsey, a prominent figure of the Hudson River School.
-
E.
Georgia Welch
Georgia Welch is best known as the wife of former U.S. Attorney General and prominent civil rights advocate Ramsey Clark.
- 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_69d7bdee64a08190801c6d470aefd723 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961d7cd4c81909521839ef5859799 |
completed | April 10, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671a8f068819086e2191439607f76 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:21 p.m.