Triple
T7921450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 18th Army Group |
E183952
|
entity |
| Predicate | MontgomeryRole |
P37119
|
FINISHED |
| Object | subordinate army commander |
—
|
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: subordinate army commander | Statement: [18th Army Group, MontgomeryRole, subordinate army commander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MontgomeryRole Context triple: [18th Army Group, MontgomeryRole, subordinate army commander]
-
A.
headquartersRole
Indicates that an entity serves in an official capacity or role at the headquarters of an organization.
-
B.
roleAtD.C.United
Indicates that an entity holds or held a specific role or position within the D.C. United soccer organization.
-
C.
roleAtGettysburg
Indicates the specific role, position, or function an entity held in relation to the Battle of Gettysburg.
-
D.
commanderRole (Banastre Tarleton)
Indicates that Banastre Tarleton held a position of command or leadership, typically over military forces or operations.
-
E.
servedInRole
chosen
Indicates that one entity performed duties or held a position within a specified role or office in relation to 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a9499cc8190b6bd81f4625c77ab |
completed | March 31, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:06 p.m.