Triple
T29461921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National War Memorial, Ottawa |
E747259
|
entity |
| Predicate | unknownSoldierInterredYear |
P71407
|
FINISHED |
| Object | 2000 |
—
|
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: 2000 | Statement: [National War Memorial, Ottawa, unknownSoldierInterredYear, 2000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unknownSoldierInterredYear Context triple: [National War Memorial, Ottawa, unknownSoldierInterredYear, 2000]
-
A.
numberOfInterred
Indicates the total count of individuals who are buried or interred at a given site or within a specified context.
-
B.
enlistmentYear
Indicates the year in which an entity formally joined or was enrolled into a service, organization, or group.
-
C.
originallyInterredPerson
Indicates that one entity is the person who was first buried or laid to rest at the location or in the grave represented by the other entity.
-
D.
hasUnknownDeathDate
Indicates that the entity’s date of death is not known or not specified.
-
E.
tombOfUnknownSoldierAdded
chosen
Indicates that a tomb of an unknown soldier has been established or incorporated at a particular location or within a commemorative context.
- 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_69f0bd4125f88190b56104591351619c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66ba455e0819092aaa13310599a71 |
completed | May 2, 2026, 9:24 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:50 p.m.