Triple
T19727962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonio and Mellida |
E473775
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Piero |
—
|
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: Piero | Statement: [Antonio and Mellida, mainCharacter, Piero]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piero Context triple: [Antonio and Mellida, mainCharacter, Piero]
-
A.
Piero
chosen
Piero was a common given name among members of the powerful Medici family that ruled Florence during the Renaissance.
-
B.
Francesco
Francesco is the Italian given name of Frank Nitti, a notorious American mobster and key figure in Al Capone’s Chicago Outfit.
-
C.
Francesco
Francesco is the given name of Italian actor Franco Nero, renowned for his iconic role in the Spaghetti Western film "Django."
-
D.
Francesco
Francesco is a masculine given name of Italian origin, derived from the Latin Franciscus and commonly associated with figures such as Saint Francis of Assisi.
-
E.
Francesco
Francesco is the birth name of Frank Capra, the renowned Italian-American film director known for classic Hollywood movies such as "It's a Wonderful Life."
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649fa1bc481908a9e7cf4fc52f75c |
completed | April 20, 2026, 3:44 p.m. |
Created at: April 10, 2026, 1:47 p.m.