Triple
T28837988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoàn Kiếm (Returned Sword) legend |
E728236
|
entity |
| Predicate | explainsToponym |
P74345
|
FINISHED |
| Object | “Hoàn Kiếm” (Returned Sword) |
—
|
NE NERFINISHED |
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: “Hoàn Kiếm” (Returned Sword) | Statement: [Hoàn Kiếm (Returned Sword) legend, explainsToponym, “Hoàn Kiếm” (Returned Sword)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: explainsToponym Context triple: [Hoàn Kiếm (Returned Sword) legend, explainsToponym, “Hoàn Kiếm” (Returned Sword)]
-
A.
toponymLiteralMeaning
chosen
Indicates the literal or etymological meaning of a place name (toponym), describing what the name directly translates to or signifies.
-
B.
toponymRefersTo
Indicates that a place name (toponym) designates or refers to a specific geographic entity or location.
-
C.
legacyToponym
Indicates that one place name is an older or former name historically used to refer to the same geographic entity as another place name.
-
D.
influenceOnToponymy
Indicates that one entity has affected or shaped the naming, form, or development of place names associated with another entity.
-
E.
toponymsShareSpelling
Indicates that two place names share the same or very similar written form or spelling.
- 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_69f0319e8e7c8190b37288c8845b9dbc |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f65b14512c8190a40e70319dcc54cd |
completed | May 2, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 6:39 a.m.