Triple
T2078234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warsaw Pact invasion of Czechoslovakia |
E44977
|
entity |
| Predicate | casualtiesCiviliansKilled |
P34802
|
FINISHED |
| Object | approximately 100 |
—
|
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: approximately 100 | Statement: [Warsaw Pact invasion of Czechoslovakia, casualtiesCiviliansKilled, approximately 100]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesCiviliansKilled Context triple: [Warsaw Pact invasion of Czechoslovakia, casualtiesCiviliansKilled, approximately 100]
-
A.
casualties
Indicates that an event, action, or situation resulted in people being killed or injured.
-
B.
casualtiesType
Indicates the specific category or nature of casualties (e.g., killed, injured, missing) associated with an event or incident.
-
C.
casualtiesKilledUS
Indicates that the relationship specifies the number of U.S. individuals who were killed as casualties in an event or incident.
-
D.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
E.
notableVictims
Indicates that the object is a person or group who is especially well-known or significant as a victim of the subject.
- 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_69a88916c2b48190a5ca2e9b12cad3ed |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abba31eef8819081cf7f5334b59fe1 |
completed | March 7, 2026, 5:40 a.m. |
| PD | Predicate disambiguation | batch_69abb7b0edac8190a58eabee55f73deb |
completed | March 7, 2026, 5:29 a.m. |
| PDg | Predicate description generation | batch_69abb85fe7a08190b991b1f23bc34f93 |
completed | March 7, 2026, 5:32 a.m. |
Created at: March 4, 2026, 7:41 p.m.