Triple
T2795247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 90th Light Africa Division |
E53019
|
entity |
| Predicate | garrisonDuringCampaign |
P11474
|
FINISHED |
| Object | various locations in Libya |
—
|
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: various locations in Libya | Statement: [90th Light Africa Division, garrisonDuringCampaign, various locations in Libya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: garrisonDuringCampaign Context triple: [90th Light Africa Division, garrisonDuringCampaign, various locations in Libya]
-
A.
garrisonDuringBattle
Indicates that an entity is stationed to defend or hold a location specifically during the time a battle is taking place.
-
B.
garrisonDuringWar
chosen
Indicates that a military force is stationed in a specific location for defense or control during a time of war.
-
C.
garrisonSize
Indicates the number of troops or defenders stationed at a particular location as its garrison.
-
D.
garrisonCommand
Indicates that one entity holds command authority over the garrison or stationed military forces at a particular location.
-
E.
garrisonCommander
Indicates that one entity serves as the commanding officer in charge of the military garrison located at or associated with another entity.
- 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_69ab495a90788190941b6917e1eca3a6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abddd48bcc819083f4ec59d66f0ece |
completed | March 7, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69abdd040f9481908e9c7a2df88ea1ae |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:58 p.m.