Triple
T8188674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Betty Mabry |
E191249
|
entity |
| Predicate | modeledFor |
P2006
|
FINISHED |
| Object | Wilhelmina Models |
E83010
|
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: Wilhelmina Models | Statement: [Betty Mabry, modeledFor, Wilhelmina Models]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wilhelmina Models Context triple: [Betty Mabry, modeledFor, Wilhelmina Models]
-
A.
Wilhelmina Models
chosen
Wilhelmina Models is a major international modeling and talent agency representing fashion models and other artists worldwide.
-
B.
Models Inc.
Models Inc. is a mid-1990s American prime-time soap opera centered on the lives and careers of models at a Los Angeles modeling agency.
-
C.
Victoria’s Secret
Victoria’s Secret is a prominent American lingerie and beauty retailer known for its fashion shows, supermodel “Angels,” and extensive line of intimate apparel and related products.
-
D.
Moda, Inc.
Moda, Inc. is a U.S.-based healthcare company that operates insurance and related health services businesses, including Moda Health.
-
E.
Maidenform
Maidenform is a well-known American lingerie and shapewear brand recognized for its bras, panties, and intimate apparel.
- 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_69ca82c5b6948190a583c096fb0a6c71 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4d9f4a488190b39bdc1792646914 |
completed | March 31, 2026, 4:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cced8437008190bf547154c2d16639 |
completed | April 1, 2026, 10:03 a.m. |
Created at: March 30, 2026, 5:41 p.m.