Triple
T38509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee |
E762
|
entity |
| Predicate | hasRomanizationOf |
P2508
|
FINISHED |
| Object | Korean surname I (이) |
—
|
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: Korean surname I (이) | Statement: [Lee, hasRomanizationOf, Korean surname I (이)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRomanizationOf Context triple: [Lee, hasRomanizationOf, Korean surname I (이)]
-
A.
hasEndonym
Indicates that an entity has a name or designation used by native speakers or within its own local language or community.
-
B.
usesDiacritics
Indicates that the referenced text or linguistic element employs diacritical marks as part of its written form.
-
C.
hasBasicLetters
Indicates that an entity contains or is composed of fundamental alphabetic characters, without additional symbols or diacritics.
-
D.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by another entity.
-
E.
isMostWidelyUsedWritingSystem
Indicates that the subject writing system is used by more people or in more contexts than any other writing system.
- F. None of above. chosen
Provenance (4 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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24b4d5bd08190a3a48eb26e67768c |
completed | Feb. 28, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69a24ab6141881908701106aa97e4735 |
completed | Feb. 28, 2026, 1:53 a.m. |
| PDg | Predicate description generation | batch_69a24b4c59b08190854b5335f5eff790 |
completed | Feb. 28, 2026, 1:56 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.