Triple
T106157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlin Blockade |
E2140
|
entity |
| Predicate | supplyCut |
P4898
|
FINISHED |
| Object | food shipments to West Berlin |
—
|
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: food shipments to West Berlin | Statement: [Berlin Blockade, supplyCut, food shipments to West Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supplyCut Context triple: [Berlin Blockade, supplyCut, food shipments to West Berlin]
-
A.
support
Indicates that one entity provides assistance, endorsement, or backing to another entity or its actions.
-
B.
usedSupplyMethod
Indicates that an entity employed a particular method or process to supply or deliver something.
-
C.
providedFor
Indicates that one entity supplies, furnishes, or makes something available to or on behalf of another entity for its use or benefit.
-
D.
offersViewOf
Indicates that one entity provides a vantage point from which another entity can be seen or visually appreciated.
-
E.
discontinuedIn
Indicates that an item, product, or service stopped being produced, offered, or supported starting in a specified time or place.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a256ec650c8190bee2067e37065527 |
completed | Feb. 28, 2026, 2:46 a.m. |
| PD | Predicate disambiguation | batch_69a2563d33788190999d471b486d5603 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a256ea776081908fec36c3fdfb8d84 |
completed | Feb. 28, 2026, 2:46 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.