Triple
T14374519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 0992.HK |
E356438
|
entity |
| Predicate | hasCorporateAnnouncements |
P74699
|
FINISHED |
| Object | published via HKEXnews |
—
|
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: published via HKEXnews | Statement: [0992.HK, hasCorporateAnnouncements, published via HKEXnews]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCorporateAnnouncements Context triple: [0992.HK, hasCorporateAnnouncements, published via HKEXnews]
-
A.
hasCorporateActionsOn
Indicates that one entity performs, records, or is associated with corporate actions (such as dividends, splits, or mergers) that affect another entity.
-
B.
hasAnnouncementsSystem
chosen
Indicates that an entity is equipped with or uses a system for creating, managing, and delivering announcements.
-
C.
announcedTo
Indicates that one entity formally communicated or made known some information, decision, or event to another specific entity.
-
D.
announcedThat
Indicates that one entity publicly communicated or declared a specific fact, decision, or piece of information about another entity or situation.
-
E.
hasCorporateActionHistory
Indicates that an entity is associated with a record or sequence of past corporate actions or events that have affected it.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de9007184c8190aebb003cb6548cc8 |
completed | April 14, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69de2a9cb3e081909f6b33fdd939bb9e |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:16 a.m.