Triple
T17710780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gypsy Girl mosaic |
E441555
|
entity |
| Predicate | comparedTo |
P278
|
FINISHED |
| Object | Mona Lisa |
—
|
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: Mona Lisa | Statement: [Gypsy Girl mosaic, comparedTo, Mona Lisa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mona Lisa Context triple: [Gypsy Girl mosaic, comparedTo, Mona Lisa]
-
A.
Mona Lisa
chosen
The Mona Lisa is Leonardo da Vinci’s iconic Renaissance portrait, renowned worldwide for its enigmatic smile and artistic mastery.
-
B.
Mona Lisa
Mona Lisa is a 1986 British neo-noir crime drama film starring Bob Hoskins and Cathy Tyson, noted for its gritty portrayal of London’s criminal underworld.
-
C.
Mona Lisa
"Mona Lisa" is a 1950 pop song famously performed by Nat King Cole, known for its smooth vocal style and enduring popularity.
-
D.
La Lisa
La Lisa is a municipality in the western part of Havana, Cuba, known primarily as a residential and industrial area.
-
E.
You and the Mona Lisa
"You and the Mona Lisa" is a folk-pop song by American singer-songwriter Shawn Colvin, known for its melodic storytelling and inclusion on her acclaimed 1990s album "A Few Small Repairs."
- 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4729b5d3c819085613ed25dc6761d |
completed | April 19, 2026, 6:13 a.m. |
Created at: April 10, 2026, 10:05 a.m.