Triple
T28566230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donald Mallard |
E722684
|
entity |
| Predicate | branchOfServiceInBackstory |
P165459
|
FINISHED |
| Object | British Army |
—
|
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: British Army | Statement: [Donald Mallard, branchOfServiceInBackstory, British Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: branchOfServiceInBackstory Context triple: [Donald Mallard, branchOfServiceInBackstory, British Army]
-
A.
branchOfServiceModelledOn
Indicates that one branch of service is modeled, structured, or designed based on another branch of service.
-
B.
branchOfServiceFocus
Indicates that one entity is the primary military or organizational branch of service emphasized, specialized in, or targeted by another entity or activity.
-
C.
militaryUnitTypeServed
Indicates that an entity served in, or was a member of, a specific type of military unit.
-
D.
placeOfMilitaryService
Indicates the location or institution where a person performed their military service.
-
E.
mainCharacterMilitaryService
Indicates that the main character has served or is serving in the military, capturing their involvement in formal armed forces service.
- F. None of above. chosen
Provenance (4 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 28, 2026, 4:07 a.m.