Triple
T25478730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Langemark German war cemetery |
E638505
|
entity |
| Predicate | numberOfBuriedInMassGrave |
P149637
|
FINISHED |
| Object | over 25000 |
—
|
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: over 25000 | Statement: [Langemark German war cemetery, numberOfBuriedInMassGrave, over 25000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfBuriedInMassGrave Context triple: [Langemark German war cemetery, numberOfBuriedInMassGrave, over 25000]
-
A.
numberOfVictimsInMassGraves
chosen
Indicates the count of individuals who were killed and buried together in mass graves associated with a particular event or context.
-
B.
numberOfMassGraves
Indicates the quantity of mass graves associated with or present at a given entity or location.
-
C.
numberOfBurials
Indicates the total count of burial events associated with a given entity.
-
D.
numberOfGravesApproximate
Indicates that the stated count of graves is an estimated or approximate number rather than an exact figure.
-
E.
massGravesDiscovered
Indicates that previously unknown burial sites containing multiple bodies have been found.
- 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_69e75db9b964819096802dcf502e577e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 21, 2026, 2:27 p.m.