Triple
T1603293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashraf Ghani |
E34442
|
entity |
| Predicate | leftCountry |
P30661
|
FINISHED |
| Object | 2021-08-15 |
—
|
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: 2021-08-15 | Statement: [Ashraf Ghani, leftCountry, 2021-08-15]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftCountry Context triple: [Ashraf Ghani, leftCountry, 2021-08-15]
-
A.
country1
Indicates that the subject entity is a country (or represents a country) in the given context.
-
B.
country2
Indicates a secondary or alternative country associated with an entity, such as a second nationality, location, or jurisdiction.
-
C.
deltaCountry
Indicates a change or difference in country between two related entities or states.
-
D.
launchCountry
Indicates the country from which an object (such as a spacecraft, missile, or satellite) is launched.
-
E.
laterCountryOfOrigin
Indicates that an entity’s country of origin changed, and this predicate specifies the country that became its origin at a later time than a previously associated country.
- 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_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. |
| PDg | Predicate description generation | batch_69a95aada3f881909053363c01de8b57 |
completed | March 5, 2026, 10:29 a.m. |
Created at: March 4, 2026, 7:28 p.m.