Triple
T19389621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Wells |
E485029
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Walter Hobbs |
—
|
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: Walter Hobbs | Statement: [Susan Wells, hasRelative, Walter Hobbs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walter Hobbs Context triple: [Susan Wells, hasRelative, Walter Hobbs]
-
A.
Walter Hobbs
chosen
Walter Hobbs is the work-obsessed children's book publisher and estranged father of Buddy in the Christmas comedy film "Elf."
-
B.
John Hobbs
John Hobbs is the alias used by the character John Canty in Mark Twain’s novel "The Prince and the Pauper."
-
C.
Robert Hobbs
Robert Hobbs is an actor known for his role in the film "Longford" and various other screen and stage performances.
-
D.
Mr. Hobbs
Mr. Hobbs is a kindly, plainspoken New York grocer who serves as a loyal friend and moral anchor to the young hero in Frances Hodgson Burnett’s novel "Little Lord Fauntleroy."
-
E.
Harvey Kinkle
Harvey Kinkle is Sabrina Spellman's kind-hearted, often clueless mortal boyfriend in the "Sabrina the Teenage Witch" franchise.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b4328448190b6347c41265e820c |
completed | April 20, 2026, 12:25 p.m. |
Created at: April 10, 2026, 1:36 p.m.