Triple
T28196909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Save Me |
E716471
|
entity |
| Predicate | hasEmotionTheme |
P41794
|
FINISHED |
| Object | heartbreak |
—
|
LITERAL 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: heartbreak | Statement: [Save Me, hasEmotionTheme, heartbreak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEmotionTheme Context triple: [Save Me, hasEmotionTheme, heartbreak]
-
A.
hasTypeOfEmotion
chosen
Indicates that an entity experiences, expresses, or is associated with a particular kind or category of emotion.
-
B.
requiresEmotion
Indicates that one entity’s occurrence, validity, or performance depends on the presence or experience of a particular emotion in another entity.
-
C.
hasMood
Indicates that an entity is experiencing or characterized by a particular emotional or affective state.
-
D.
hasEmotionalIntensity
Indicates that an emotion, experience, or expression is characterized by a particular degree or strength of emotional impact.
-
E.
hasEmote
Indicates that an entity expresses or is associated with a particular emotion or emotive expression.
- F. None of above.
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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 10:28 p.m.