Triple
T6018972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drew Roy |
E134015
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Sugar Mountain |
E472193
|
NE FINISHED |
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: Sugar Mountain | Statement: [Drew Roy, notableWork, Sugar Mountain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sugar Mountain Context triple: [Drew Roy, notableWork, Sugar Mountain]
-
A.
Sugar Mountain
chosen
"Sugar Mountain" is a beloved Neil Young song, written when he was a teenager, that nostalgically reflects on the loss of youth and innocence.
-
B.
Sweet Marie
Sweet Marie is the titular woman addressed in Bob Dylan’s song “Absolutely Sweet Marie,” serving as the elusive, symbolic love interest at the center of the lyrics.
-
C.
Round Midnight
"Round Midnight" is a jazz standard composed by Thelonious Monk that has become one of the most recorded and celebrated pieces in the jazz repertoire.
-
D.
Moonlight Mile
Moonlight Mile is a crime novel by Dennis Lehane that revisits private investigators Patrick Kenzie and Angela Gennaro as they confront the consequences of a child abduction case from their past.
-
E.
Mother Hill
Mother Hill is an English name referring to Mam Tor, a prominent and landslide-prone hill in the Peak District of Derbyshire.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c008742a5c8190b9cb9c2787a3d8b3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f8589d0819089ae7840461640f6 |
completed | March 22, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1136da26081909b753fa8a2a91084 |
completed | March 23, 2026, 10:18 a.m. |
Created at: March 22, 2026, 4:07 p.m.