Triple
T4868759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Learning to Fly |
E109034
|
entity |
| Predicate | hasBside |
P15273
|
FINISHED |
| Object | Too Good to Be True |
E340800
|
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: Too Good to Be True | Statement: [Learning to Fly, hasBside, Too Good to Be True]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Too Good to Be True Context triple: [Learning to Fly, hasBside, Too Good to Be True]
-
A.
"Too Good to Be True"
chosen
"Too Good to Be True" is a musical number featured in Disney's 1947 animated package film *Fun and Fancy Free*.
-
B.
I Could Not Believe It Was True
"I Could Not Believe It Was True" is a country song featured as one of the tracks on Willie Nelson’s concept album *Red Headed Stranger*.
-
C.
Tell Me That It Isn't True
"Tell Me That It Isn't True" is a country-influenced song by Bob Dylan featured on his late-1960s album Nashville Skyline.
-
D.
Truth Is
"Truth Is" is a soulful R&B ballad by American singer Fantasia Barrino, released as one of her breakout singles following her American Idol victory.
-
E.
She Was Too Good to Me
"She Was Too Good to Me" is a 1974 jazz album by trumpeter and vocalist Chet Baker that marked his celebrated comeback after years away from the recording scene.
- 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_69bd440d96a48190b0c87069adef2af1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d7d809081909fc7c80c56f72840 |
completed | March 20, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be67ea7cd88190b89f5cc1d85c1994 |
completed | March 21, 2026, 9:42 a.m. |
Created at: March 20, 2026, 1:27 p.m.