Triple
T15715097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Hobbs |
E380940
|
entity |
| Predicate | childOf |
P120
|
FINISHED |
| Object | Emily Hobbs |
E372962
|
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: Emily Hobbs | Statement: [Michael Hobbs, childOf, Emily Hobbs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emily Hobbs Context triple: [Michael Hobbs, childOf, Emily Hobbs]
-
A.
Emily Hobbs
chosen
Emily Hobbs is the young daughter of Walter Hobbs in the Christmas film "Elf," who helps her family embrace Buddy and the holiday spirit.
-
B.
Louise Hobbs
Louise Hobbs is best known as the wife of British actor and television presenter Tony Robinson.
-
C.
Moira Banning
Moira Banning is a fictional character from the 1991 fantasy film "Hook," where she appears as Peter Banning's wife in Steven Spielberg's reimagining of the Peter Pan story.
-
D.
Toni Mannix
Toni Mannix was an American actress and longtime mistress of Superman actor George Reeves, known for her connections to Hollywood’s Golden Age and the enduring mystery surrounding Reeves’s death.
-
E.
Amy Prentiss
Amy Prentiss is a 1970s American television crime drama series featuring Jessica Walter as a pioneering female chief of detectives in San Francisco.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f90aea0819082a9e9fe0f7780b0 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff7581302c8190918266f04bcf2231 |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:45 a.m.