Triple
T20071649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gigi Hadid |
E499752
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | IMG Models |
—
|
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: IMG Models | Statement: [Gigi Hadid, employer, IMG Models]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IMG Models Context triple: [Gigi Hadid, employer, IMG Models]
-
A.
IMG Models (historically)
chosen
IMG Models is a leading international modeling agency known for representing many of the world’s most prominent fashion models and talent.
-
B.
IMG
IMG is a global sports, events, and talent management company known for representing athletes and models and producing major sporting and fashion events.
-
C.
Imagen Foundation
Imagen Foundation is a nonprofit organization dedicated to promoting positive and accurate portrayals of Latinos in the entertainment industry, best known for organizing the annual Imagen Awards.
-
D.
VisionEncoderDecoderModel
VisionEncoderDecoderModel is a Hugging Face Transformers architecture that combines a vision encoder with a text decoder to perform tasks like image captioning and visual question answering.
-
E.
DALL·E
DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66438633481908710907c48806499 |
completed | April 20, 2026, 5:36 p.m. |
Created at: April 11, 2026, 3:40 p.m.