Triple
T18502380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gloria Blondell |
E452109
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Gloria Blondell |
—
|
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: Gloria Blondell | Statement: [Gloria Blondell, name, Gloria Blondell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gloria Blondell Context triple: [Gloria Blondell, name, Gloria Blondell]
-
A.
Gloria Blondell
chosen
Gloria Blondell was an American film, radio, and television actress of the mid-20th century, known for her character roles and as the younger sister of actress Joan Blondell.
-
B.
Gloria Swenson
Gloria Swenson is the tough, streetwise former mob moll who becomes an unlikely protector of a young boy in the crime thriller film "Gloria."
-
C.
Gloria Connors
Gloria Connors was an American tennis coach best known as the mother and early mentor of tennis champion Jimmy Connors.
-
D.
Gloria Millington
Gloria Millington is a fictional character from the "Kingdom" series, known for her role within its dramatic, character-driven storyline.
-
E.
Gloria Rand
Gloria Rand is a Canadian actress best known as the first wife of actor William Shatner.
- 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_69d8d3855d50819097fc8561b0299dd9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e532c535908190bdc90c58fc5bdaf7 |
completed | April 19, 2026, 7:53 p.m. |
Created at: April 10, 2026, 11:36 a.m.