Triple
T29009051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Armenia Alliance |
E736512
|
entity |
| Predicate | includesFormerOfficialsOf |
P112779
|
FINISHED |
| Object | Government of Armenia |
—
|
NE NERFINISHED |
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: Government of Armenia | Statement: [Armenia Alliance, includesFormerOfficialsOf, Government of Armenia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesFormerOfficialsOf Context triple: [Armenia Alliance, includesFormerOfficialsOf, Government of Armenia]
-
A.
includesOfficials
Indicates that one entity contains or encompasses certain officials as part of its composition or scope.
-
B.
formerOfficialIn
Indicates that an entity once held an official position or office within another entity but no longer does.
-
C.
hasMemberWhoHeldOffice
chosen
Indicates that a group or organization includes at least one member who has held a specified office or position.
-
D.
includesOfficeHoldersFrom
Indicates that something (such as a group, list, or organization) contains or encompasses office holders originating from a specified source or set.
-
E.
involvedOfficeHolders
Indicates that certain office holders participated in, were associated with, or played a role in a particular event, action, or entity.
- 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_69f077eb81e88190ad9ff62cbb9f555e |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ff5f5ecc808190b2df364da108ff4c |
completed | May 9, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69ff5b84131c8190bf81d7fb53e934bc |
completed | May 9, 2026, 4:06 p.m. |
Created at: April 28, 2026, 9:40 a.m.