Triple
T23615338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Do You Really Want to Hurt Me |
E583156
|
entity |
| Predicate | helpedEstablishAsStar |
P71399
|
FINISHED |
| Object | Boy George |
—
|
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: Boy George | Statement: [Do You Really Want to Hurt Me, helpedEstablishAsStar, Boy George]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpedEstablishAsStar Context triple: [Do You Really Want to Hurt Me, helpedEstablishAsStar, Boy George]
-
A.
hasStarOn
Indicates that one entity bears or displays a star symbol positioned on another entity.
-
B.
hasStars
Indicates that an entity possesses or is associated with one or more stars.
-
C.
starIs
chosen
Indicates that one entity is identified or classified as a star in relation to another entity or context.
-
D.
establishedAs
Indicates that one entity is formally created, designated, or recognized in a particular role, status, or identity as another entity.
-
E.
typicalStar
Indicates that an entity is a representative or characteristic example of stars in general, exhibiting the usual or expected properties of stars.
- 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_69e248fbcd9081908ba08913f9d30826 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b0f71a2481909c3d0d8d0d58e20f |
completed | April 29, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:45 p.m.