Triple
T8382590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kwan |
E197729
|
entity |
| Predicate | isVariantOfSurname |
P16885
|
FINISHED |
| Object | Gwan |
E197729
|
NE 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: Gwan | Statement: [Kwan, isVariantOfSurname, Gwan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwan Context triple: [Kwan, isVariantOfSurname, Gwan]
-
A.
Gwan-eum
Gwan-eum is the Korean name for Guanyin, the bodhisattva of compassion widely revered in East Asian Buddhism.
-
B.
Wintuan
Wintuan is a small group of Native American languages historically spoken in northern California, often classified within the proposed Penutian language phylum.
-
C.
Gan
Gan is a common abbreviated name and historical-cultural designation for Jiangxi Province in southeastern China.
-
D.
Kwan
chosen
Kwan is a Chinese-origin surname shared by many individuals, including the renowned American figure skater Michelle Kwan.
-
E.
Ganlu
Ganlu was a historical Chinese era name used during the Cao Wei state of the Three Kingdoms period.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82f64c188190af4e1608036b865d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cbd120a1ec8190a8dc101fa1371780 |
completed | March 31, 2026, 1:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde814816481909bcc3b11fa5a1367 |
completed | April 2, 2026, 3:52 a.m. |
Created at: March 30, 2026, 6:02 p.m.