Triple
T30961170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baraza |
E788827
|
entity |
| Predicate | oftenChairedBy |
P97952
|
FINISHED |
| Object | local elder |
—
|
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: local elder | Statement: [Baraza, oftenChairedBy, local elder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenChairedBy Context triple: [Baraza, oftenChairedBy, local elder]
-
A.
sometimesChairedBy
chosen
Indicates that an entity occasionally serves as the chair or leader of another entity, but not on a regular or permanent basis.
-
B.
coChairpersonOf
Indicates that a person serves jointly with one or more others as the chairperson of a group, organization, or committee.
-
C.
chairpersonUsuallyFrom
Indicates that the person serving as chairperson typically originates from or is selected from the specified group, organization, or category.
-
D.
hasBoardChairperson
Indicates that an entity has a specific person serving as the chairperson of its board.
-
E.
hasCoChairFrom
Indicates that an entity has a co-chair whose affiliation or origin is from a specified source, organization, or group.
- 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 29, 2026, 8:54 p.m.