Triple
T12201894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Ghost |
E290734
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | "I Get High" |
E290736
|
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: "I Get High" | Statement: [The Ghost, notableSong, "I Get High"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: "I Get High" Context triple: [The Ghost, notableSong, "I Get High"]
-
A.
I Get High
chosen
"I Get High" is a popular hip-hop single by rapper Styles P, best known for its smooth, soulful production and its candid celebration of marijuana use.
-
B.
U Get Me High
"U Get Me High" is a rock song by Tom Petty and the Heartbreakers, featured on their 2014 album *Hypnotic Eye*.
-
C.
She’s So High
"She’s So High" is a pop-rock song by British singer-songwriter Tal Bachman, best known for its soaring chorus and late-1990s chart success.
-
D.
C.R.E.A.M.
C.R.E.A.M. is a seminal Wu-Tang Clan track that explores the struggles of poverty and the pursuit of money, widely regarded as one of the most influential hip-hop songs of the 1990s.
-
E.
You’re Makin’ Me High
"You’re Makin’ Me High" is a 1996 sultry R&B single by Toni Braxton that became one of her signature hits, topping the Billboard Hot 100 and earning critical acclaim.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91c7b97408190a11ea37cc6edf18c |
completed | April 10, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a982e308190979245ac9643465a |
completed | May 2, 2026, 2:30 p.m. |
Created at: April 8, 2026, 9:51 p.m.