Triple
T13794879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thursday |
E331488
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Gone |
E65303
|
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: Gone | Statement: [Thursday, hasTrack, Gone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gone Context triple: [Thursday, hasTrack, Gone]
-
A.
Gone
chosen
"Gone" is a reflective hip-hop track by Kanye West featuring Consequence and Cam'ron, known for its soulful Otis Redding sample and intricate storytelling.
-
B.
Gone
"Gone" is a suspense thriller novel by bestselling American crime writer Lisa Gardner, featuring a high-stakes kidnapping investigation and psychological tension.
-
C.
Gone
"Gone" is a punk rock song by The Bouncing Souls, known for its melodic hooks and emotionally charged lyrics about loss and moving on.
-
D.
Gone
"Gone" is a country music album by American singer-songwriter Dwight Yoakam that blends traditional honky-tonk with more contemporary influences.
-
E.
Gone
"Gone" is a crime thriller novel in the Michael Bennett series by James Patterson, following the NYPD detective as he confronts a vengeful crime lord he once helped put away.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0259b0e4819081c11ced694384fb |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b083387081909c6f4beb0e12cf36 |
completed | May 3, 2026, 8:30 p.m. |
Created at: April 9, 2026, 10:11 p.m.