Triple
T13102303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Taurit |
E310746
|
entity |
| Predicate | memorialSubject |
P63144
|
FINISHED |
| Object | victims of the Siege of Leningrad |
—
|
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: victims of the Siege of Leningrad | Statement: [Robert Taurit, memorialSubject, victims of the Siege of Leningrad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorialSubject Context triple: [Robert Taurit, memorialSubject, victims of the Siege of Leningrad]
-
A.
isCommemorationSubject
chosen
Indicates that an entity serves as the focus or object of a commemorative act, event, or artifact.
-
B.
memorialName
Indicates that a memorial is known by or designated with a particular name.
-
C.
memorialWork
Indicates that one entity is a commemorative work (such as a monument, plaque, or artwork) created to honor or remember another entity.
-
D.
commemoratedFor
Indicates that one entity is honored, remembered, or celebrated because of a particular action, achievement, event, or characteristic associated with it.
-
E.
relatedMemorial
Indicates a relationship where one entity serves as a memorial or commemorative reference to another entity.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d981515d488190908d3cca1b84a42d |
completed | April 10, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69d98041a3548190a05ddd83dbb660fa |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:04 p.m.