Triple
T3903597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | People's Democratic Party of Afghanistan |
E90551
|
entity |
| Predicate | reasonForLossOfPower |
P52786
|
FINISHED |
| Object | collapse of Soviet support |
—
|
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: collapse of Soviet support | Statement: [People's Democratic Party of Afghanistan, reasonForLossOfPower, collapse of Soviet support]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForLossOfPower Context triple: [People's Democratic Party of Afghanistan, reasonForLossOfPower, collapse of Soviet support]
-
A.
lostPowerIn
Indicates that an entity has experienced a loss of electrical or functional power while in or at a specified location or context.
-
B.
lostPower
Indicates that an entity has ceased to have electrical or functional power it previously possessed.
-
C.
lostPowerDuring
Indicates that an entity ceased to have electrical or functional power at some time during a specified event or interval.
-
D.
lostPowerInEvent
Indicates that an entity ceased to have power or electricity as a result of a specific event.
-
E.
lostPowerAgainIn
Indicates that an entity has experienced a repeated loss of power in a specified location or context.
- 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_69aed95d315881908cbf1bf4a7215fbf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef1abe2dc81909c18aeae9b286898 |
completed | March 9, 2026, 4:13 p.m. |
| PD | Predicate disambiguation | batch_69aee75cff148190b6d5979d17fae085 |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aef1aada308190821a3dfa6af170b3 |
completed | March 9, 2026, 4:13 p.m. |
Created at: March 9, 2026, 3:22 p.m.