Triple
T658657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delhi English |
E11704
|
entity |
| Predicate | mediumOf |
P166
|
FINISHED |
| Object | everyday communication in Delhi |
—
|
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: everyday communication in Delhi | Statement: [Delhi English, mediumOf, everyday communication in Delhi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumOf Context triple: [Delhi English, mediumOf, everyday communication in Delhi]
-
A.
usedMedium
Indicates that an action or communication was carried out through a particular medium or channel.
-
B.
primaryMedium
Indicates the main material, format, or channel through which something is created, expressed, or communicated.
-
C.
secondaryMedium
Indicates that an entity is associated with an additional, non-primary medium or channel through which it is expressed, delivered, or communicated.
-
D.
medium
chosen
Indicates that an entity serves as the means, channel, or intermediary through which an action, communication, or effect is carried out between other entities.
-
E.
mediaType
Indicates the format or category of media associated with an entity, such as text, image, audio, or video.
- 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_69a4932862a0819098be659c814e4981 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a0f55f7481909e052a25bd12d455 |
completed | March 1, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69a49d1406ec8190abf546549264c85d |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.