Triple
T19318068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Party City |
E483149
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Party City |
—
|
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: Party City | Statement: [Party City, brand, Party City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Party City Context triple: [Party City, brand, Party City]
-
A.
Party City
chosen
Party City is a retail chain specializing in party supplies, decorations, and costumes for events and celebrations.
-
B.
Party Central
Party Central is a Pixar animated short film set in the Monsters University universe, featuring Mike Wazowski and Sulley throwing a wild fraternity party.
-
C.
Olympia Entertainment
Olympia Entertainment is a Detroit-based sports and entertainment company that manages major venues and events, including professional sports arenas and historic theaters.
-
D.
Wonder Bar
Wonder Bar is a famous beachfront bar and live music venue in Asbury Park, New Jersey, known for its iconic Tillie mural and role in the local rock scene.
-
E.
Wonder Bar
Wonder Bar is a 1934 American pre-Code musical film adaptation of a Broadway show, known for its blend of comedy, music, and controversial themes.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d85046c81909d972a6b369b0c2b |
completed | April 20, 2026, 11:27 a.m. |
Created at: April 10, 2026, 1:32 p.m.