Triple
T14374521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 0992.HK |
E356438
|
entity |
| Predicate | hasShareRegistrar |
P88611
|
FINISHED |
| Object | a Hong Kong share registrar appointed by Lenovo Group Limited |
—
|
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: a Hong Kong share registrar appointed by Lenovo Group Limited | Statement: [0992.HK, hasShareRegistrar, a Hong Kong share registrar appointed by Lenovo Group Limited]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShareRegistrar Context triple: [0992.HK, hasShareRegistrar, a Hong Kong share registrar appointed by Lenovo Group Limited]
-
A.
hasRegistrar
chosen
Indicates that an entity is formally recorded or overseen by a specific registrar organization or authority.
-
B.
hasShareClass
Indicates that an entity is associated with a specific class or category of shares that defines distinct rights or characteristics of ownership.
-
C.
hasOwnerShare
Indicates that an entity holds a specified ownership stake or share in another entity or asset.
-
D.
hasRegister
Indicates that one entity possesses, contains, or is associated with a specific register (such as a record, log, or hardware register).
-
E.
sharesRegistrationWith
Indicates that two or more entities are associated with the same registration identifier or record.
- 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.