Triple
T19140185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heart |
E468534
|
entity |
| Predicate | hasSingle |
P3282
|
FINISHED |
| Object | “Heart On Fire” |
—
|
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: “Heart On Fire” | Statement: [Heart, hasSingle, “Heart On Fire”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Heart On Fire” Context triple: [Heart, hasSingle, “Heart On Fire”]
-
A.
“Heart On Fire”
chosen
“Heart On Fire” is a song whose title evokes intense passion and emotional turmoil, often associated with themes of love and desire.
-
B.
Heart on Fire
"Heart on Fire" is a country song by American singer-songwriter Eric Church, known for its nostalgic lyrics and energetic, rock-influenced sound.
-
C.
Hearts on Fire
"Hearts on Fire" is a high-energy rock song best known for its appearance in the training montage of the 1985 film Rocky IV.
-
D.
Hearts on Fire
"Hearts on Fire" is a melodic bass track by electronic music producer Illenium, known for its emotional lyrics, soaring synths, and cinematic drops.
-
E.
When Your Heart’s on Fire
"When Your Heart’s on Fire" is a jazz vocal album by American singer and pianist Jeri Southern, showcasing her intimate, torch-song style interpretations.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3f094f88190996279d7b548edea |
completed | April 20, 2026, 8:29 a.m. |
Created at: April 10, 2026, 12:05 p.m.