Triple
T34253620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French 16th Division |
E878811
|
entity |
| Predicate | usedMachineGuns |
P820
|
FINISHED |
| Object | Hotchkiss machine gun |
—
|
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: Hotchkiss machine gun | Statement: [French 16th Division, usedMachineGuns, Hotchkiss machine gun]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedMachineGuns Context triple: [French 16th Division, usedMachineGuns, Hotchkiss machine gun]
-
A.
lightArmament
Indicates that an entity is equipped with or characterized by relatively minimal or lightweight weaponry compared to standard or heavy armament.
-
B.
Berdan No.1 rifle
Indicates that an entity is a Berdan No.1 rifle, i.e., it has the identity or classification of that specific rifle model.
-
C.
weaponsUsed
chosen
Indicates that one entity employed or utilized another entity as a weapon in carrying out an action or event.
-
D.
standardIssueMachineGun
Indicates that an entity is equipped with or uses the standard-issue machine gun designated for its organization, faction, or context.
-
E.
numberOfGuns
Indicates the quantity of guns associated with a given entity or situation.
- 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_69f349b421cc8190b4b4655e1d612548 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:56 a.m.