Triple
T13168672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singori sweet |
E312917
|
entity |
| Predicate | isTraditionallyMadeWith |
P12771
|
FINISHED |
| Object | hand-prepared khoya |
—
|
LITERAL 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: hand-prepared khoya | Statement: [Singori sweet, isTraditionallyMadeWith, hand-prepared khoya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTraditionallyMadeWith Context triple: [Singori sweet, isTraditionallyMadeWith, hand-prepared khoya]
-
A.
traditionallyUsedBy
Indicates that something has been customarily or historically used by a particular person, group, or culture over time.
-
B.
isUsuallyCookedIn
Indicates that something is most commonly or typically prepared or cooked within a particular container, appliance, or environment.
-
C.
traditionallyServed
Indicates that one entity is customarily or conventionally presented, offered, or consumed together with another entity.
-
D.
usesIngredient
chosen
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
-
E.
traditionallyBelievedToContain
Indicates that something is customarily or historically thought to include or hold something else, regardless of whether this belief is factually accurate.
- F. None of above.
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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bc2c0c88190be357811aa8e828d |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:13 p.m.