Triple
T20045575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adam Beach |
E497548
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Smoke Signals |
—
|
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: Smoke Signals | Statement: [Adam Beach, notableWork, Smoke Signals]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Smoke Signals Context triple: [Adam Beach, notableWork, Smoke Signals]
-
A.
Smoke Signals
Smoke Signals is a music album by American actor and musician Mark Salling, known for his role on the television series Glee.
-
B.
Smoke Signals
chosen
Smoke Signals is a 1998 independent film based on Sherman Alexie’s stories that explores contemporary Native American life through a road trip and family drama.
-
C.
Smoke Signal
Smoke Signal is a track by the band Cahoots, likely reflecting their indie/alternative style and thematic focus.
-
D.
War Dance
War Dance is a track featured on the album "Goons Be Gone" by the American post-punk band No Age.
-
E.
The Fire Theft
The Fire Theft is an American rock band formed by former Sunny Day Real Estate members, known for its melodic, emotionally driven sound and intricate songwriting.
- 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_69da627278c88190babe4297a9df1236 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6632a5e888190ade41657ffd057f6 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:37 p.m.