Triple
T20772645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William F. Garrison |
E511273
|
entity |
| Predicate | hasRankAtEvent |
P58134
|
FINISHED |
| Object | Major General during the Battle of Mogadishu |
—
|
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: Major General during the Battle of Mogadishu | Statement: [William F. Garrison, hasRankAtEvent, Major General during the Battle of Mogadishu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRankAtEvent Context triple: [William F. Garrison, hasRankAtEvent, Major General during the Battle of Mogadishu]
-
A.
hasRankContext
chosen
Indicates that an entity’s rank or ordering is defined, interpreted, or constrained within a specific contextual framework or situation.
-
B.
hasRankCategory
Indicates that an entity is assigned to a particular rank-based classification or level within an ordered hierarchy.
-
C.
containsRank
Indicates that one entity includes or encompasses another entity that has a specific rank or hierarchical level within it.
-
D.
isRanked
Indicates that an entity has been assigned a position or level within an ordered hierarchy or comparative list.
-
E.
hasCoSanctionedEventWith
Indicates that two or more entities have jointly imposed or participated in the same sanction-related event or action.
- 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_69e0b4ca01148190ac018e57e0cab46f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2681ff88190bfe5938c2db6b2c4 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:37 p.m.