Triple
T18199919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David |
E435754
|
entity |
| Predicate | diminutiveForm |
P456
|
FINISHED |
| Object | Davie |
—
|
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: Davie | Statement: [David, diminutiveForm, Davie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Davie Context triple: [David, diminutiveForm, Davie]
-
A.
Davie
chosen
Davie is a diminutive or affectionate form of the given name David, commonly used in English-speaking contexts.
-
B.
Davie Village
Davie Village is a vibrant LGBTQ+ hub in Vancouver known for its rainbow crosswalks, nightlife, and inclusive community spaces.
-
C.
Davie, Florida
Davie, Florida is a suburban town in Broward County known for its western-themed architecture, equestrian lifestyle, and proximity to the Miami–Fort Lauderdale metropolitan area.
-
D.
Bayah
Bayah is a coastal town and district in Lebak Regency, Banten, Indonesia, known historically for its mining activities and beaches along the Indian Ocean.
-
E.
Lauderdale
Lauderdale is a small suburban city in Ramsey County, Minnesota, situated within the Minneapolis–Saint Paul metropolitan area.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0d610f88190b4f69b1c433ea6b1 |
completed | April 19, 2026, 2:04 p.m. |
Created at: April 10, 2026, 10:31 a.m.