Triple
T37299473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 99th Infantry Division |
E925899
|
entity |
| Predicate | enteredCombatTheater |
P47252
|
FINISHED |
| Object | Belgium |
—
|
NE NERFINISHED |
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: Belgium | Statement: [99th Infantry Division, enteredCombatTheater, Belgium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredCombatTheater Context triple: [99th Infantry Division, enteredCombatTheater, Belgium]
-
A.
enteredCombatInEurope
chosen
Indicates that an entity became actively involved in military combat operations within the geographical region of Europe.
-
B.
enteredUSArmyService
Indicates that an individual began active service in the United States Army at a specific point in time.
-
C.
firstCombatOperation
Indicates that the referenced combat operation is the earliest or initial combat action undertaken by the entity in question.
-
D.
enteredNATOService
Indicates that an entity (typically a military asset or unit) began active operational service under NATO command or within NATO forces.
-
E.
sawCombatInRegion
Indicates that an entity participated in combat operations within a specified geographic region.
- 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_69f76eb0f86c819098dee07393e69ec3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbc9d1dba881908c399b8e1dc13ce2 |
completed | May 6, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:16 p.m.