Triple
T19105717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дмитрий Андреевич Муратов |
E467647
|
entity |
| Predicate | цель продажи медали |
P134394
|
FINISHED |
| Object | помощь украинским беженцам (через UNICEF) |
—
|
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: помощь украинским беженцам (через UNICEF) | Statement: [Дмитрий Андреевич Муратов, цель продажи медали, помощь украинским беженцам (через UNICEF)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: цель продажи медали Context triple: [Дмитрий Андреевич Муратов, цель продажи медали, помощь украинским беженцам (через UNICEF)]
-
A.
medalFor
Indicates that a medal is awarded to an entity in recognition of a specific achievement, action, or service.
-
B.
medalIn
Indicates that an entity has received a medal or award in a particular event, field, or competition.
-
C.
medalType
Indicates the specific category or class of a medal associated with an award or achievement.
-
D.
originalMedal
Indicates that a medal is the first or authentic instance awarded, rather than a copy, replacement, or later version.
-
E.
materialOfMedal
Indicates that a specified material is the substance from which a particular medal is made.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e37159688190a6896d9730214ba8 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
| PDg | Predicate description generation | batch_69e4bfe8a06081909fd5c28a33e9f218 |
completed | April 19, 2026, 11:43 a.m. |
Created at: April 10, 2026, 12:04 p.m.