Triple
T28154500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Austro-Hungarian Army ranks |
E714704
|
entity |
| Predicate | includesBranchSpecificRanks |
P36072
|
FINISHED |
| Object | cavalry ranks |
—
|
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: cavalry ranks | Statement: [Austro-Hungarian Army ranks, includesBranchSpecificRanks, cavalry ranks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesBranchSpecificRanks Context triple: [Austro-Hungarian Army ranks, includesBranchSpecificRanks, cavalry ranks]
-
A.
hasSeparateRanking
Indicates that an entity is evaluated or ordered independently from others, with its own distinct ranking.
-
B.
containsRank
Indicates that one entity includes or encompasses another entity that has a specific rank or hierarchical level within it.
-
C.
compilerRank
Indicates the relative ranking or priority assigned to a compiler compared to other compilers.
-
D.
rankStructureIncludes
chosen
Indicates that a given rank structure contains or encompasses a specified rank or set of ranks within its hierarchy.
-
E.
usesRankStructure
Indicates that an entity organizes its members or components according to a defined hierarchical rank structure.
- 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_69efd6b033208190bf74f80a147e2092 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fec4cffed08190b5e5e7cc0c87493e |
completed | May 9, 2026, 5:23 a.m. |
| PD | Predicate disambiguation | batch_69fec2ea7fe08190bd751b39515f69d1 |
completed | May 9, 2026, 5:15 a.m. |
Created at: April 27, 2026, 10:01 p.m.