Triple
T31452052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amir of Afghanistan |
E802348
|
entity |
| Predicate | abolishedOrTransformed |
P30300
|
FINISHED |
| Object | early 20th century |
—
|
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: early 20th century | Statement: [Amir of Afghanistan, abolishedOrTransformed, early 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: abolishedOrTransformed Context triple: [Amir of Afghanistan, abolishedOrTransformed, early 20th century]
-
A.
abolishedDuring
chosen
Indicates that an entity or practice ceased to exist or was officially ended within the time period defined by another entity.
-
B.
abolishedAfter
Indicates that one entity was abolished at a later time than another entity was abolished.
-
C.
abolishedToCreate
Indicates that one entity is formally ended, eliminated, or discontinued for the purpose of establishing or bringing into existence another entity.
-
D.
wasAbolishedBy
Indicates that an institution, practice, law, or entity ceased to exist or operate as a result of an action taken by another entity.
-
E.
abolishedDuringGovernmentOf
Indicates that something (such as a law, institution, or practice) was officially ended or eliminated while a particular government was in power.
- 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_69f348c678ac81908a2e950867619061 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:14 p.m.