Triple
T22470032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patti McGuire |
E555470
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Patti |
—
|
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: Patti | Statement: [Patti McGuire, givenName, Patti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patti Context triple: [Patti McGuire, givenName, Patti]
-
A.
Patti
Patti is a historic town in the Tarn Taran district of Punjab, India, known for its agricultural surroundings and cultural heritage.
-
B.
Patti
chosen
Patti is the given name of Patti LuPone, the acclaimed American actress and singer best known for her work in musical theatre on Broadway and the West End.
-
C.
Patti
Patti is a coastal town in northeastern Sicily, Italy, known for its historic center, archaeological sites, and beaches along the Tyrrhenian Sea.
-
D.
Pattie
Pattie is the given name of Dame Pattie Menzies, the wife of former Australian Prime Minister Sir Robert Menzies and a notable public figure in her own right.
-
E.
Patty
Patty is a supporting character in the Peanuts comic strip, known as one of the original children in Charlie Brown’s neighborhood.
- 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_69e11e52c2048190952dc5df209b9bed |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15bdeae9c8190a5b66e540484db37 |
completed | April 29, 2026, 1:16 a.m. |
Created at: April 16, 2026, 8:48 p.m.