Triple
T1603292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashraf Ghani |
E34442
|
entity |
| Predicate | leftOfficeFollowing |
P171
|
FINISHED |
| Object | Taliban takeover of Kabul in 2021 |
—
|
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: Taliban takeover of Kabul in 2021 | Statement: [Ashraf Ghani, leftOfficeFollowing, Taliban takeover of Kabul in 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftOfficeFollowing Context triple: [Ashraf Ghani, leftOfficeFollowing, Taliban takeover of Kabul in 2021]
-
A.
leftOffice
chosen
Indicates that an entity ceased holding or performing the duties of a particular office or position.
-
B.
followsWork
Indicates that one work (such as a publication, version, or creative piece) comes directly after another in sequence or succession.
-
C.
followedByCabinet
Indicates that one entity (typically a government or administration) is immediately succeeded in office or function by a specific cabinet.
-
D.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
E.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a95b02cd448190be8e3db9a5a7bac0 |
completed | March 5, 2026, 10:29 a.m. |
| PD | Predicate disambiguation | batch_69a907c1cad08190b9728dd557f39aa0 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.