Triple
T7724179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma |
E175086
|
entity |
| Predicate | romanizationUsage |
P23170
|
FINISHED |
| Object | personal names |
—
|
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: personal names | Statement: [Ma, romanizationUsage, personal names]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizationUsage Context triple: [Ma, romanizationUsage, personal names]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
romanizationBegan
Indicates that the process of converting text from one writing system into its representation using the Roman (Latin) alphabet was initiated.
-
C.
usesKatakanaFor
Indicates that one entity is written or represented using katakana script in relation to another entity.
-
D.
hasRomanizationStandard
chosen
Indicates that an entity’s romanized form follows a specified romanization standard or system.
-
E.
hasHakkaRomanization
Indicates that an entity is associated with a specific representation of its name or term in Hakka Romanization.
- 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:05 p.m.