Triple
T21150249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 孔祥熙 |
E521167
|
entity |
| Predicate | 家族集团 |
P8006
|
FINISHED |
| Object | 孔宋家族 |
—
|
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: 孔宋家族 | Statement: [孔祥熙, 家族集团, 孔宋家族]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 家族集团 Context triple: [孔祥熙, 家族集团, 孔宋家族]
-
A.
familyGroup
Indicates that multiple entities are related to each other as members of the same family unit or household.
-
B.
parentCompanyFoundedByFamily
Indicates that the parent company was established or originally created by a family or family members.
-
C.
relatedFamilyBusiness
chosen
Indicates that there is a connection between entities through ownership, management, or involvement in the same family-run business or businesses.
-
D.
organizationalFamily
Indicates that one organization is related to another as part of the same organizational family, such as parent, subsidiary, or affiliate within a shared corporate or institutional structure.
-
E.
familyType
Indicates the specific familial relationship or category that characterizes how the related entities are connected as family.
- 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_69e0b50c6a848190a4e525a77a319b8a |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72400911c8190978e88138a9bfaff |
completed | April 21, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69e5f5f8a5bc819081918c7fa8e4496d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 2:58 p.m.