Triple
T20622000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Needles and Pins |
E506720
|
entity |
| Predicate | lyricist |
P1360
|
FINISHED |
| Object | Sonny Bono |
—
|
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: Sonny Bono | Statement: [Needles and Pins, lyricist, Sonny Bono]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonny Bono Context triple: [Needles and Pins, lyricist, Sonny Bono]
-
A.
Sonny Bono
chosen
Sonny Bono was an American singer, songwriter, actor, and politician best known as half of the pop duo Sonny & Cher and later as a U.S. Congressman from California.
-
B.
Phillip Burton
Phillip Burton was a powerful and influential Democratic U.S. Congressman from California known for his liberal politics and major role in expanding the national park system and social welfare programs in the mid-20th century.
-
C.
Doug LaMalfa
Doug LaMalfa is a Republican politician and farmer who serves as a U.S. Representative from Northern California.
-
D.
Dan Roberts
Dan Roberts is a Canadian musician best known as the bassist for the rock band Crash Test Dummies.
-
E.
Tom Pepper
Tom Pepper is an American software developer best known as a co-creator of the peer-to-peer file-sharing service Gnutella.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe25c208190af057bcd1aa6219d |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.