Triple
T25661917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cassirer family |
E643405
|
entity |
| Predicate | hasOccupationOfMembers |
P112780
|
FINISHED |
| Object | art dealer |
—
|
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: art dealer | Statement: [Cassirer family, hasOccupationOfMembers, art dealer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOccupationOfMembers Context triple: [Cassirer family, hasOccupationOfMembers, art dealer]
-
A.
hasMemberWhoHeldOccupation
chosen
Indicates that a group or collective entity includes at least one member who has held a specified occupation.
-
B.
endedOccupationOf
Indicates that one entity brought another entity’s occupation or control of a place or position to an end.
-
C.
hasNonClericalMembers
Indicates that an organization or group includes members who are not part of the clergy or formal religious leadership.
-
D.
representedOccupation
Indicates that one entity has served as an official or formal representative of another entity’s occupation or professional role.
-
E.
commonProfessionAmongBearers
Indicates that multiple entities sharing a given attribute (such as a name or title) are frequently associated with the same profession.
- 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_69e77e7e45648190a068ed3faa8016ea |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5faf04d488190a47674ff847204cf |
completed | May 2, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f4807f8680819098a524158d049c63 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 6:55 p.m.