Triple
T2197459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marshal of the Soviet Union |
E50408
|
entity |
| Predicate | lastConferred |
P1462
|
FINISHED |
| Object | 1990 |
—
|
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: 1990 | Statement: [Marshal of the Soviet Union, lastConferred, 1990]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastConferred Context triple: [Marshal of the Soviet Union, lastConferred, 1990]
-
A.
conferredOn
Indicates that something (such as an honor, title, degree, or benefit) has been formally granted or bestowed upon a particular entity.
-
B.
lastAwarded
chosen
Indicates the most recent time or instance at which an entity received a particular award.
-
C.
conferredIn
Indicates that something (such as a degree, title, or honor) was formally granted or awarded within a particular context, event, or institution.
-
D.
awardedSince
Indicates that an entity has been receiving a particular award continuously from a specified starting time onward.
-
E.
lastAppearance
Indicates the most recent time or instance in which an entity appears or is present within a given context or sequence.
- 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_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbf79f3e08190b56e9d7c0ff27237 |
completed | March 7, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69abbda706f4819094de73e1d1d1f539 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.