Triple
T36659235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Jude Byrnes |
E905074
|
entity |
| Predicate | succeededAsArchbishopOfAgaña |
P202460
|
FINISHED |
| Object | 2018-03-16 |
—
|
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: 2018-03-16 | Statement: [Michael Jude Byrnes, succeededAsArchbishopOfAgaña, 2018-03-16]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: succeededAsArchbishopOfAgaña Context triple: [Michael Jude Byrnes, succeededAsArchbishopOfAgaña, 2018-03-16]
-
A.
appointedCoadjutorArchbishopOfAgaña
Indicates that someone was formally appointed to serve as the coadjutor archbishop of the Archdiocese of Agaña.
-
B.
appointedAsArchbishop
Indicates that an authority formally assigned a person to hold the office or role of an archbishop.
-
C.
electedAsArchbishopOn
Indicates that an entity was chosen and formally appointed to the position of archbishop on a specific date.
-
D.
enthronedAsMajorArchbishopOn
Indicates that someone was formally installed in office with the rank and authority of a Major Archbishop on a specific date or occasion.
-
E.
successorAsBishopOfManila
Indicates that one person assumed the position of Bishop of Manila directly after another, succeeding them in that ecclesiastical office.
- F. None of above. chosen
Provenance (4 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_69f76e6e3b908190970251b30f76ad71 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00818b20a881909fbf3bb33dcf7029 |
completed | May 10, 2026, 1 p.m. |
| PD | Predicate disambiguation | batch_6a0080f76f588190a933238861243d1a |
completed | May 10, 2026, 12:58 p.m. |
| PDg | Predicate description generation | batch_6a00818a671c819086d487dd5a5ba5d7 |
completed | May 10, 2026, 1 p.m. |
Created at: May 3, 2026, 4:11 p.m.