Triple
T23225492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rain (Madonna music video) |
E581001
|
entity |
| Predicate | hairStyleOfMadonna |
P95511
|
FINISHED |
| Object | short black bob wig |
—
|
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: short black bob wig | Statement: [Rain (Madonna music video), hairStyleOfMadonna, short black bob wig]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hairStyleOfMadonna Context triple: [Rain (Madonna music video), hairStyleOfMadonna, short black bob wig]
-
A.
hairStyleInMedia
chosen
Indicates that a particular hairstyle is depicted or represented in a specific media work or context.
-
B.
hairStyleInPSA
Indicates that an entity has a particular hairstyle as depicted in a specific public service announcement (PSA).
-
C.
hairStyleForRole
Indicates that a particular hairstyle is designated or used for a specific role or character.
-
D.
hairAsSymbol
Indicates that hair functions as a symbolic element representing ideas, traits, or meanings beyond its literal physical presence.
-
E.
hasHair
Indicates that an entity possesses hair as a physical attribute.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922d30b08190a3c54bab58f5c8e7 |
completed | April 29, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:08 p.m.