Triple
T37104709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pingtang County |
E918809
|
entity |
| Predicate | hasSpokenLanguages |
P35567
|
FINISHED |
| Object | Southwestern Mandarin |
—
|
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: Southwestern Mandarin | Statement: [Pingtang County, hasSpokenLanguages, Southwestern Mandarin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpokenLanguages Context triple: [Pingtang County, hasSpokenLanguages, Southwestern Mandarin]
-
A.
languagesSpoken
Indicates that an entity is able to communicate using one or more specified languages.
-
B.
includesLanguagesSpokenBy
Indicates that one entity contains or covers the set of languages spoken by another entity.
-
C.
hasLanguages
chosen
Indicates that an entity is associated with one or more languages it uses, supports, or is expressed in.
-
D.
includesLanguagesSpokenAlong
Indicates that something (such as a region, route, or area) encompasses or contains the set of languages spoken along its extent or within its boundaries.
-
E.
isSpokenLanguage
Indicates that a language is used primarily for oral communication by speakers, as opposed to being only written or symbolic.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fedfd913f48190bdcd450980868d9a |
completed | May 9, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fedf58c6e88190821a7156054c9086 |
completed | May 9, 2026, 7:16 a.m. |
Created at: May 3, 2026, 4:14 p.m.