Triple
T36067069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MacTaggart |
E1043261
|
entity |
| Predicate | originalSocialRole |
P118249
|
FINISHED |
| Object | clerical family |
—
|
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: clerical family | Statement: [MacTaggart, originalSocialRole, clerical family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalSocialRole Context triple: [MacTaggart, originalSocialRole, clerical family]
-
A.
socialRoleIn
Indicates that one entity holds a particular social role, status, or position within the context or framework defined by another entity.
-
B.
roleInOrigin
chosen
Indicates that an entity holds or held a specific role, function, or position within the context of its origin or source.
-
C.
primaryRoleFor
Indicates that one entity serves as the main or most important role or function for another entity.
-
D.
socialRoleInWork
Indicates the role or position an entity holds within a work-related or professional social context.
-
E.
originalReleaseRole
Indicates the specific role an entity played in the original release of a work, such as how it contributed or participated in that initial publication or distribution.
- 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_69f76e2fd3248190b900d9a492bf5a7a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:08 p.m.