Triple
T21862601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B.O. Plenty |
E539801
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Gravel Gertie |
—
|
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: Gravel Gertie | Statement: [B.O. Plenty, hasRelative, Gravel Gertie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gravel Gertie Context triple: [B.O. Plenty, hasRelative, Gravel Gertie]
-
A.
Gravel Gertie
chosen
Gravel Gertie is a comic-strip character from the "Dick Tracy" series, known as the eccentric and homely wife of B.O. Plenty.
-
B.
Waddy
Waddy is a given name most notably borne by the American architect Waddy Butler Wood.
-
C.
Gertie
Gertie is the young girl, played by Drew Barrymore, who befriends the alien in the classic science fiction film "E.T. the Extra-Terrestrial."
-
D.
Bony Lizzie
Bony Lizzie is a malevolent witch character from Joseph Delaney’s "Spook’s" (Wardstone Chronicles) series, known for her dark magic and familial ties to the powerful witch Mother Malkin.
-
E.
Peutie
Peutie is a village in Flemish Brabant, Belgium, that forms a residential suburb of the nearby city of Vilvoorde.
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d63beb00819092b8ec3a8ef55a39 |
completed | April 28, 2026, 3:46 p.m. |
Created at: April 16, 2026, 6:56 p.m.