Triple
T8514951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karen Kwan |
E201548
|
entity |
| Predicate | familyRelationToMichelleKwan |
P7844
|
FINISHED |
| Object | older sister |
—
|
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: older sister | Statement: [Karen Kwan, familyRelationToMichelleKwan, older sister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: familyRelationToMichelleKwan Context triple: [Karen Kwan, familyRelationToMichelleKwan, older sister]
-
A.
familyOf
Indicates a familial relationship exists between the entities, such as by blood, marriage, or adoption.
-
B.
motherIsMemberOf
Indicates that the person identified as the mother belongs to or is part of a specified group, organization, or collection.
-
C.
parentOfCelebrity
Indicates that one entity is the parent of another entity who is a celebrity.
-
D.
hasFamilialTieTo
chosen
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
-
E.
familyRelationToEmperor
Indicates that one entity is related to an emperor by family ties, specifying a kinship or familial connection between them.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60e12848190a4a3dfa457aef275 |
completed | March 31, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69cbd10cfd208190a519049fad32c508 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:15 p.m.