Triple
T20695978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Passerella |
E508659
|
entity |
| Predicate | taxonomicScope |
P53195
|
FINISHED |
| Object | New World |
—
|
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: New World | Statement: [Passerella, taxonomicScope, New World]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New World Context triple: [Passerella, taxonomicScope, New World]
-
A.
New World
chosen
The New World refers to the Western Hemisphere, especially the Americas, as distinguished from the Old World of Europe, Asia, and Africa.
-
B.
New World
New World is a South Korean crime thriller film in which Lee Jung-jae plays a central role in a tense story of undercover operations and power struggles within a powerful crime syndicate.
-
C.
New World
"New World" is the closing song of the 2000 musical drama film *Dancer in the Dark*, written and performed by Björk.
-
D.
New World
New World is a New Zealand-based supermarket chain and retail brand.
-
E.
New World
New World is the English title of the Japanese crime thriller film "Shinsekai," known for its gritty depiction of underworld power struggles.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c11180e481908423385fbe97ab26 |
completed | April 21, 2026, 12:13 a.m. |
Created at: April 16, 2026, 12:10 p.m.