Triple
T10284883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love Letters |
E241201
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Gladys Cooper |
E321398
|
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: Gladys Cooper | Statement: [Love Letters, castMember, Gladys Cooper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gladys Cooper Context triple: [Love Letters, castMember, Gladys Cooper]
-
A.
Gladys Cooper
chosen
Gladys Cooper was a distinguished English stage and film actress known for her poised, often austere character roles in classic Hollywood and British cinema.
-
B.
Gladys McConnell
Gladys McConnell was an American film actress of the silent and early sound era, known for her roles in Westerns and adventure serials.
-
C.
Gladys George
Gladys George was an American stage and film actress known for her character roles in classic Hollywood cinema, including a notable appearance in the 1941 film "The Maltese Falcon."
-
D.
Gladys Murray
Gladys Murray was the wife of Sir Malcolm Murray, a British baronet and military officer.
-
E.
Gladys Joyce Walsh
Gladys Joyce Walsh was the wife of American film and television actor Grant Withers.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2b737788190bfadd0d48ad38f5b |
completed | April 7, 2026, 9:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a4d8a3481909c7f8a529d0051c2 |
completed | May 2, 2026, 2:29 p.m. |
Created at: April 6, 2026, 11:40 a.m.