Triple
T14258534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Saint-Dizier |
E353448
|
entity |
| Predicate | hasOffensiveForceType |
P41989
|
FINISHED |
| Object | field army |
—
|
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: field army | Statement: [Siege of Saint-Dizier, hasOffensiveForceType, field army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOffensiveForceType Context triple: [Siege of Saint-Dizier, hasOffensiveForceType, field army]
-
A.
hasOpposingForceType
Indicates that one force is characterized as being of a type that opposes or counteracts another force.
-
B.
offensiveForce
chosen
Indicates the use or application of aggressive or attacking power or violence by one entity against another.
-
C.
enemyForceType
Indicates that one entity is characterized as a hostile or opposing force of a specified type relative to another entity.
-
D.
offensiveStrength
Indicates the degree or capacity of an entity to carry out effective attacks or aggressive actions against an opponent.
-
E.
isOffensiveWeapon
Indicates that something qualifies as a weapon designed or used to cause harm or injury, typically in an aggressive or unlawful 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6352611c819090d062fe3079cd03 |
completed | April 14, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69de2a7d586c8190846ff242bbf5ac53 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:09 a.m.