Triple
T31500317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xi |
E803659
|
entity |
| Predicate | hasPinyinTonePattern |
P86299
|
FINISHED |
| Object | xí |
—
|
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: xí | Statement: [Xi, hasPinyinTonePattern, xí]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPinyinTonePattern Context triple: [Xi, hasPinyinTonePattern, xí]
-
A.
hasPhonemicTone
Indicates that a language, word, or syllable uses pitch differences (tones) as phonemic contrasts that can change meaning.
-
B.
hasVariantWithoutToneMarks
Indicates that one textual form is a variant of another in which all tone marks have been removed.
-
C.
romanizesTonePattern
Indicates that one entity converts the tonal pattern of another entity’s language or script into a romanized (Latin alphabet) representation.
-
D.
mandarinTone
chosen
Indicates the specific tonal pattern in Mandarin Chinese with which an entity (such as a syllable or word) is pronounced.
-
E.
usesToneMarks
Indicates that one entity applies or includes diacritical tone marks in the representation or transcription of another entity (such as text, language, or symbols).
- 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_69f348cae52081909fa8e5f697523ae3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 30, 2026, 9:43 p.m.