Triple
T4880810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nina Agdal |
E109320
|
entity |
| Predicate | hasWorkedFor |
P11675
|
FINISHED |
| Object | CoverGirl |
E51749
|
NE 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: CoverGirl | Statement: [Nina Agdal, hasWorkedFor, CoverGirl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CoverGirl Context triple: [Nina Agdal, hasWorkedFor, CoverGirl]
-
A.
CoverGirl
chosen
CoverGirl is a major American cosmetics brand known for its mass-market makeup products and high-profile celebrity spokesmodels.
-
B.
Maybelline New York
Maybelline New York is a major American cosmetics and beauty brand known worldwide for its mass-market makeup products.
-
C.
Kylie Cosmetics
Kylie Cosmetics is a makeup and beauty brand founded by Kylie Jenner, known for its trend-setting lip kits and social media–driven marketing.
-
D.
Revlon
Revlon is a major American cosmetics, skincare, fragrance, and personal care company known for its mass-market beauty products and global brand presence.
-
E.
Benefit Cosmetics
Benefit Cosmetics is a San Francisco–born beauty brand known for its playful packaging and bestselling brow and complexion products, and is part of the luxury group LVMH.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6dc071d4819083ea9fd0c73c5f49 |
completed | March 20, 2026, 3:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be6803a1c081908972984241276c19 |
completed | March 21, 2026, 9:42 a.m. |
Created at: March 20, 2026, 1:27 p.m.