Triple
T13320549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsinan |
E317302
|
entity |
| Predicate | transcriptionOf |
P84620
|
FINISHED |
| Object | Mandarin pronunciation of 济南 |
—
|
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: Mandarin pronunciation of 济南 | Statement: [Tsinan, transcriptionOf, Mandarin pronunciation of 济南]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transcriptionOf Context triple: [Tsinan, transcriptionOf, Mandarin pronunciation of 济南]
-
A.
isTranscriptionOf
Indicates that one entity is a written, typed, or otherwise recorded representation of the content of another entity, preserving its original form as closely as possible.
-
B.
transcription
Indicates the process by which genetic information in DNA is copied into RNA by RNA polymerase.
-
C.
transcribedAs
chosen
Indicates that one entity is a written or recorded representation of another entity’s content, typically converting it from one form (e.g., audio, handwriting) into text.
-
D.
alsoTranscribes
Indicates that an entity, in addition to its primary transcription role, transcribes another specified entity as well.
-
E.
transcriptAvailable
Indicates that a transcript of the referenced content is available for access or use.
- 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cfdc9388190af1fdd3cd4717bd8 |
completed | April 11, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69d98f6babd88190a5d529df9584b9a4 |
completed | April 11, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:30 p.m.