Triple
T26417000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swish Swish |
E664122
|
entity |
| Predicate | hasRumoredSubtext |
P162334
|
FINISHED |
| Object | celebrity feud |
—
|
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: celebrity feud | Statement: [Swish Swish, hasRumoredSubtext, celebrity feud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRumoredSubtext Context triple: [Swish Swish, hasRumoredSubtext, celebrity feud]
-
A.
usesDoubleEntendre
Indicates that one entity employs language or expressions with a double meaning, often to convey a hidden or suggestive message alongside a literal one.
-
B.
hasRomanticSubplot
Indicates that a work includes a secondary storyline centered on a romantic relationship between characters.
-
C.
romanticMisunderstandingsWith
Indicates a situation where two entities experience confusion, misinterpretation, or mistaken beliefs about each other’s romantic feelings, intentions, or relationship status.
-
D.
secretlyIs
Indicates that one entity possesses a hidden or undisclosed identity, role, or attribute in relation to another entity.
-
E.
rumoredLoverOf
Indicates that one entity is widely believed or speculated to be the romantic partner or lover of another entity, without confirmed evidence.
- F. None of above. chosen
Provenance (4 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_69ee883a04ec81908883c4559f8c7e24 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6250321088190ae3ed1dc9f2fcd03 |
completed | May 2, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69f623a7539c8190b71797f583da9f63 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f62473a38481909b919f88ffb5b492 |
completed | May 2, 2026, 4:21 p.m. |
Created at: April 26, 2026, 11:41 p.m.