Triple
T3001189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhang |
E81790
|
entity |
| Predicate | romanizedFrom |
P2508
|
FINISHED |
| Object | Chinese character 张 |
—
|
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: Chinese character 张 | Statement: [Zhang, romanizedFrom, Chinese character 张]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizedFrom Context triple: [Zhang, romanizedFrom, Chinese character 张]
-
A.
hasRomanizationOf
chosen
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
hasRomanizationStandard
Indicates that an entity’s romanized form follows a specified romanization standard or system.
-
C.
usesKatakanaFor
Indicates that one entity is written or represented using katakana script in relation to another entity.
-
D.
usesKanjiFrom
Indicates that one writing system, word, or text incorporates or is composed of kanji characters originating from another specified source.
-
E.
hasRomanizationContrast
Indicates that there is a meaningful difference between two or more romanized representations of the same original form.
- 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_69ad8b1c4de88190a83b7cefaa1f2842 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a1022e48190afee77db94635ff2 |
completed | March 8, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69ad9615fefc8190ad96da92519cb7a3 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:59 p.m.