Triple
T20109705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexandra Bellow |
E490293
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bellow |
—
|
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: Bellow | Statement: [Alexandra Bellow, familyName, Bellow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bellow Context triple: [Alexandra Bellow, familyName, Bellow]
-
A.
Saul Bellow
chosen
Saul Bellow was a Canadian-born American novelist and Nobel Prize laureate renowned for his richly intellectual, character-driven explorations of modern urban life and the search for meaning.
-
B.
Janis Freedman Bellow
Janis Freedman Bellow is an American scholar and writer best known as the widow and literary executor of Nobel Prize–winning novelist Saul Bellow.
-
C.
Bashevis
Bashevis is the literary pseudonym used by Nobel Prize–winning Yiddish author Isaac Bashevis Singer.
-
D.
Les Grossman
Les Grossman is a foul-mouthed, overbearing Hollywood studio executive portrayed by Tom Cruise in the satirical action-comedy film "Tropic Thunder."
-
E.
William Gaddis
William Gaddis was an American postmodern novelist known for his dense, allusive, and formally experimental works such as "The Recognitions" and "JR."
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e666df1b148190a28ead2f7cce7aab |
completed | April 20, 2026, 5:48 p.m. |
Created at: April 11, 2026, 11:28 p.m.