Triple
T3232804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 21 Signal Regiment |
E67780
|
entity |
| Predicate | hasHierarchyLevel |
P2393
|
FINISHED |
| Object | regiment |
—
|
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: regiment | Statement: [21 Signal Regiment, hasHierarchyLevel, regiment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHierarchyLevel Context triple: [21 Signal Regiment, hasHierarchyLevel, regiment]
-
A.
hasHierarchyIn
Indicates that one entity occupies a higher or lower level within an ordered structure or chain of command relative to another entity in a specified context.
-
B.
hasLevel
chosen
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
-
C.
hasNumberOfLevels
Indicates that an entity possesses a specified count of distinct levels or tiers.
-
D.
isPartOfHierarchyWith
Indicates that one entity occupies a defined position within an ordered or nested structure relative to another entity in the same hierarchy.
-
E.
hasMultipleLevels
Indicates that something is organized into more than one hierarchical or structural level.
- 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_69ad858c61888190a31196310d9b30b5 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaedb718c8190aae12f763033713a |
completed | March 8, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ada4159e0481908cbbdd750f5e08c7 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:08 p.m.