Triple
T29186305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radha Shyamasundar |
E739877
|
entity |
| Predicate | ShyamasundarRefersTo |
P133801
|
FINISHED |
| Object | Krishna |
—
|
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: Krishna | Statement: [Radha Shyamasundar, ShyamasundarRefersTo, Krishna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ShyamasundarRefersTo Context triple: [Radha Shyamasundar, ShyamasundarRefersTo, Krishna]
-
A.
refersToCharacter
Indicates that one entity makes reference to, mentions, or points to a specific character as its subject.
-
B.
refersToPerson
Indicates that one entity is making reference to, mentioning, or pointing specifically to a particular person.
-
C.
alsoRefersTo
Indicates that one term, label, or identifier is used as an alternative designation for the same entity or concept as another.
-
D.
refersToDeityName
chosen
Indicates that one entity mentions, designates, or is associated with the name of a deity.
-
E.
refersToPersonFrom
Indicates that one entity makes reference to, mentions, or is about a person originating from or associated with a particular place or group.
- 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_69f07cb74c2c8190ad396487fcb4fde6 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6638722fc819098f18314dfa88a6c |
completed | May 2, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, noon