Triple
T16693556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Donnell |
E405653
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Gidget |
E885351
|
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: Gidget | Statement: [Jeff Donnell, notableWork, Gidget]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gidget Context triple: [Jeff Donnell, notableWork, Gidget]
-
A.
Gidget
Gidget is a fluffy white Pomeranian dog from the animated film "The Secret Life of Pets," known for her energetic personality and strong affection for the main dog, Max.
-
B.
Gidget
Gidget is a 1960s American TV sitcom about a fun-loving teenage surfer girl, widely recognized for launching Sally Field’s career.
-
C.
Gidget
chosen
Gidget is a 1959 American teen romantic comedy film that helped popularize surf culture and starred Sandra Dee in the title role.
-
D.
Gidget Goes to Rome
Gidget Goes to Rome is a 1963 romantic comedy film in the Gidget series that follows the teenage heroine’s adventures and misadventures during a trip to Rome.
-
E.
Blue Gillespie
Blue Gillespie is a Welsh progressive metal band fronted by actor and musician Gareth David-Lloyd.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37eab93a081909aedc45f3f8f0e10 |
completed | April 18, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00919acd308190a3f29040554b9cfc |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.