Triple
T21745729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dylan Piper |
E536781
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Gwen Piper |
—
|
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: Gwen Piper | Statement: [Dylan Piper, relative, Gwen Piper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwen Piper Context triple: [Dylan Piper, relative, Gwen Piper]
-
A.
Gwen Piper
chosen
Gwen Piper is the cautious, magic-using mother in Disney’s Halloweentown film series who tries to keep her children away from their witch heritage and the supernatural world.
-
B.
Helene Hadfield
Helene Hadfield is the wife of Canadian astronaut Chris Hadfield and is known for her role in supporting his space career and public outreach.
-
C.
Karen Crane
Karen Crane is known as the daughter of the late American actor and "Hogan's Heroes" star Bob Crane.
-
D.
Dorothy Pecaut
Dorothy Pecaut was a local conservation advocate and philanthropist whose support for environmental education and natural preservation led to a nature center being named in her honor.
-
E.
Jean Platt
Jean Platt is known as the wife of American film and theater producer Marc Platt.
- 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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a76540c8190b91a67f4a70869fb |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 16, 2026, 6:49 p.m.