Triple
T21872038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union |
E540025
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Saving My Heart |
E1506751
|
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: Saving My Heart | Statement: [Union, hasPart, Saving My Heart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saving My Heart Context triple: [Union, hasPart, Saving My Heart]
-
A.
Saving My Heart
chosen
"Saving My Heart" is a melodic pop-rock song by the English progressive rock band Yes, featured on their 1991 album *Union*.
-
B.
Protect My Heart
"Protect My Heart" is a song by the American rock band Tasty.
-
C.
Save Your Heart for Me
"Save Your Heart for Me" is a 1965 pop song by Gary Lewis & the Playboys that became one of the group's biggest chart hits.
-
D.
Keep Me in Your Heart
"Keep Me in Your Heart" is a poignant farewell ballad by Warren Zevon, widely regarded as one of his most moving and enduring songs.
-
E.
The One I Gave My Heart To
"The One I Gave My Heart To" is a soulful R&B ballad by Aaliyah, noted for its powerful vocals and emotional portrayal of heartbreak and betrayal.
- 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f3368d488190a37224b587858ab0 |
completed | April 28, 2026, 5:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a59fafb7c81908c174cda37c198fe |
completed | May 18, 2026, 12:14 a.m. |
Created at: April 16, 2026, 6:59 p.m.