Triple
T14603969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Firefly |
E342777
|
entity |
| Predicate | hasSong |
P20452
|
FINISHED |
| Object | Giannina Mia |
E1108533
|
NE FINISHED |
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: Giannina Mia | Statement: [The Firefly, hasSong, Giannina Mia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Giannina Mia Context triple: [The Firefly, hasSong, Giannina Mia]
-
A.
Giannina Mia
chosen
Giannina Mia is a popular romantic song from the early 20th century operetta "The Firefly," composed by Rudolf Friml.
-
B.
Marinella
Marinella is a popular French song famously performed by singer and actor Tino Rossi.
-
C.
Clelia Matania
Clelia Matania was an Italian actress known for her work in mid-20th-century cinema and television, including roles in notable international films.
-
D.
Maria Paiato
Maria Paiato is an Italian actress known for her work in film, television, and theater, often praised for her intense and nuanced character portrayals.
-
E.
Nina Romina
Nina Romina is a ruthless local TV news director in the film "Nightcrawler," known for her willingness to exploit violent crime footage to boost ratings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822dec68081908c2553145c4051dc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb43a1bb48190bf520cb961f15b5e |
completed | April 14, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde169eb6481909d7fac6d984a2af1 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:25 a.m.