Triple
T17397727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gorakhnath |
E422996
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Yoga |
—
|
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: Yoga | Statement: [Gorakhnath, associatedWith, Yoga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yoga Context triple: [Gorakhnath, associatedWith, Yoga]
-
A.
Yoga
Yoga is a residential and commercial neighborhood in Setagaya, Tokyo, known for its convenient transport links and urban lifestyle.
-
B.
Yoga
Yoga is Lenovo’s line of versatile laptops and 2-in-1 convertible devices known for their flexible hinges and portable design.
-
C.
Jóga
"Jóga" is a 1997 song by Icelandic artist Björk, known for its dramatic string arrangements and emotional intensity, often cited as one of her signature tracks.
-
D.
Hatha Yoga
chosen
Hatha Yoga is a branch of yoga focused on physical postures, breath control, and purification practices that aims to prepare the body and mind for higher meditative states.
-
E.
Yoganics
Yoganics is an organic food and lifestyle company co-founded by Laura Louie, known for promoting sustainable, health-conscious living.
- 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43abe6f708190944aad636e1eb9a1 |
completed | April 19, 2026, 2:15 a.m. |
Created at: April 10, 2026, 5:45 a.m.