Triple
T38079021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caturmahārāja |
E950799
|
entity |
| Predicate | equivalentTermInKorean |
P103662
|
FINISHED |
| Object | Sacheonwang |
—
|
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: Sacheonwang | Statement: [Caturmahārāja, equivalentTermInKorean, Sacheonwang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: equivalentTermInKorean Context triple: [Caturmahārāja, equivalentTermInKorean, Sacheonwang]
-
A.
equivalentTitleInKorean
chosen
Indicates that one title has an equivalent or corresponding title expressed in the Korean language.
-
B.
meaningInKorean
Indicates that one entity expresses the meaning or translation of another entity in the Korean language.
-
C.
equivalentIn
Indicates that two entities are considered logically or functionally the same in meaning, status, or effect within a given context.
-
D.
suffixMeaningOf_ko
Indicates that the suffix “ko” expresses a particular meaning or grammatical function in relation to the base word or stem.
-
E.
equivalentInTibet
Indicates that two entities are considered equivalent or correspond to each other within the context of Tibet.
- 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_69f76f02a6c48190a94f3c0b3ee90cf2 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcc7338120819081cb46547d60f2cb |
completed | May 7, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
Created at: May 3, 2026, 4:21 p.m.