Triple
T9425812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanity 6 |
E227260
|
entity |
| Predicate | song |
P20452
|
FINISHED |
| Object |
Make-Up
"Make-Up" is a funk-influenced pop song by Vanity 6, the female trio assembled and produced by Prince in the early 1980s.
|
E798172
|
NE FINISHED |
How this triple was built (4 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: Make-Up | Statement: [Vanity 6, song, Make-Up]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Make-Up Context triple: [Vanity 6, song, Make-Up]
-
A.
Mascara
Mascara is a city in northwestern Algeria known for its historical significance and role in the resistance led by Emir Abdelkader.
-
B.
The Basis of Make-Up
The Basis of Make-Up is an experimental film project by Heinz Emigholz that meticulously documents and visually interprets his sketchbooks, blending drawing, text, and cinematic form.
-
C.
BEAUTY
BEAUTY is the radio callsign used by the Belgian leisure airline TUI fly Belgium for its flight operations.
-
D.
Sleek MakeUP
Sleek MakeUP is a British cosmetics brand known for its affordable, highly pigmented makeup products and inclusive shade ranges.
-
E.
Dermablend
Dermablend is a professional-grade cosmetic brand known for its high-coverage, dermatologist-tested makeup products designed to conceal skin imperfections and provide long-lasting wear.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Make-Up Triple: [Vanity 6, song, Make-Up]
Generated description
"Make-Up" is a funk-influenced pop song by Vanity 6, the female trio assembled and produced by Prince in the early 1980s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Make-Up Target entity description: "Make-Up" is a funk-influenced pop song by Vanity 6, the female trio assembled and produced by Prince in the early 1980s.
-
A.
Mascara
Mascara is a city in northwestern Algeria known for its historical significance and role in the resistance led by Emir Abdelkader.
-
B.
The Basis of Make-Up
The Basis of Make-Up is an experimental film project by Heinz Emigholz that meticulously documents and visually interprets his sketchbooks, blending drawing, text, and cinematic form.
-
C.
BEAUTY
BEAUTY is the radio callsign used by the Belgian leisure airline TUI fly Belgium for its flight operations.
-
D.
Sleek MakeUP
Sleek MakeUP is a British cosmetics brand known for its affordable, highly pigmented makeup products and inclusive shade ranges.
-
E.
Dermablend
Dermablend is a professional-grade cosmetic brand known for its high-coverage, dermatologist-tested makeup products designed to conceal skin imperfections and provide long-lasting wear.
- F. None of above. chosen
Provenance (5 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_69ca8436ba308190903e470776d2d893 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7c908738819081df35c632f35f04 |
completed | April 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d107da6aa88190a015ee4a6eea2a4a |
completed | April 4, 2026, 12:45 p.m. |
| NEDg | Description generation | batch_69d1087d01b08190aa4d17241244c26c |
completed | April 4, 2026, 12:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d109042fec819087371150d2c2cf87 |
completed | April 4, 2026, 12:50 p.m. |
Created at: March 30, 2026, 7:49 p.m.