Triple
T24196650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNTAC |
E599851
|
entity |
| Predicate | militaryForceCommander |
P1061
|
FINISHED |
| Object | John Sanderson |
—
|
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: John Sanderson | Statement: [UNTAC, militaryForceCommander, John Sanderson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryForceCommander Context triple: [UNTAC, militaryForceCommander, John Sanderson]
-
A.
combatant2Commander
Indicates that a combatant serves under the authority or command of a specific commander.
-
B.
commander
chosen
Indicates that one entity holds authoritative military or organizational control over another entity or group.
-
C.
chiefOfGeneralStaff
Indicates that a person holds the position of Chief of the General Staff in relation to a specific military organization or armed forces.
-
D.
UnionCommanderOfAssault
Indicates that the subject served as the commanding Union officer in charge of a specific military assault.
-
E.
jointOperationsCommander
Indicates that one entity serves as the commander responsible for overseeing joint operations involving multiple forces or organizations 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e24ad83c819084ac9e34d2cc2120 |
completed | April 29, 2026, 10:49 a.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:36 p.m.