Triple
T19908080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gold |
E478471
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Firecracker |
—
|
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: Firecracker | Statement: [Gold, hasTrack, Firecracker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firecracker Context triple: [Gold, hasTrack, Firecracker]
-
A.
Firecracker
chosen
Firecracker is a darkly comic coming-of-age novel by David Iserson about a disgraced, sharp-tongued heiress navigating life at a desert reform school.
-
B.
Firecracker
Firecracker is a lightweight, open-source virtualization technology developed by AWS for running secure, multi-tenant container and function workloads using microVMs.
-
C.
Firecrackers
Firecrackers is a 1925 novel by Carl Van Vechten that satirically portrays the hedonistic, bohemian social life of Jazz Age New York.
-
D.
Firework
"Firework" is a 2010 pop anthem by Katy Perry known for its uplifting message of self-empowerment and its colorful, visually striking music video.
-
E.
Fireworks
Fireworks is a discontinued bitmap and vector graphics editor developed by Macromedia (later Adobe) that was widely used for creating and optimizing web graphics and user interface designs.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6598d91ac8190be6abdd7d1542aec |
completed | April 20, 2026, 4:51 p.m. |
Created at: April 10, 2026, 1:52 p.m.