Triple
T23766127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alibaba Group founders |
E587381
|
entity |
| Predicate | languageOfEarlyOperations |
P99698
|
FINISHED |
| Object | Chinese |
—
|
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: Chinese | Statement: [Alibaba Group founders, languageOfEarlyOperations, Chinese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfEarlyOperations Context triple: [Alibaba Group founders, languageOfEarlyOperations, Chinese]
-
A.
languageOfEarlyServices
Indicates the language in which early services (such as initial or preliminary sessions, programs, or interventions) are conducted.
-
B.
hasPrimaryLanguageOfOperations
Indicates that an entity conducts its main activities or operations primarily using a specified language.
-
C.
languageOfOperation
Indicates the language in which an entity (such as a system, service, or process) primarily operates or functions.
-
D.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
E.
languageOfEarlyDevelopment
chosen
Indicates that a specified language is used during the initial or formative stages of an entity’s development.
- 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_69e2490b8ac48190a6b35f1d5500486b |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bdb5b0408190b46661d80e37b509 |
completed | April 29, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:15 p.m.