Triple
T22368838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATL |
E552983
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | New New |
—
|
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 New | Statement: [ATL, mainCharacter, New New]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New New Context triple: [ATL, mainCharacter, New New]
-
A.
New New
chosen
New New is the protagonist of the 2006 film "ATL," a coming-of-age drama set in Atlanta’s hip-hop and roller-skating culture.
-
B.
New
New is the respondent in the U.S. Supreme Court case Wilson v. New, which addressed federal authority over labor disputes in the railroad industry.
-
C.
NEW
NEW is the standard three-letter abbreviation used to represent Newcastle Jets FC, a professional football club based in Newcastle, Australia.
-
D.
NEW
NEW is the vehicle registration code for the German town of Neustadt an der Waldnaab in Bavaria.
-
E.
Nouvel
Nouvel is a French surname most prominently associated with Jean Nouvel, the renowned contemporary architect known for his innovative and experimental building designs worldwide.
- 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_69e11e4affcc8190ba7c27d29062558d |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1580229688190a6e5e02b484033f7 |
completed | April 29, 2026, 12:59 a.m. |
Created at: April 16, 2026, 8:44 p.m.