Triple
T520450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Corps of Signals |
E10802
|
entity |
| Predicate | capBadgeFeature |
P4681
|
FINISHED |
| Object | figure of Mercury |
—
|
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: figure of Mercury | Statement: [Royal Corps of Signals, capBadgeFeature, figure of Mercury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capBadgeFeature Context triple: [Royal Corps of Signals, capBadgeFeature, figure of Mercury]
-
A.
badge
chosen
Indicates that one entity confers, displays, or is associated with a symbolic mark or emblem representing status, achievement, role, or affiliation in relation to another entity.
-
B.
badgeShape
Indicates the geometric form or outline that a badge takes.
-
C.
emblemFeatures
Indicates that an emblem includes or displays specific visual elements or characteristics.
-
D.
protectiveEmblemName
Indicates that a given name is the designated title or label of a protective emblem associated with an entity or context.
-
E.
addsProtectiveEmblem
Indicates that one entity applies or attaches a protective emblem or symbol 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_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1a00a6c8190a62dc7c901c2f2ff |
completed | Feb. 28, 2026, 1:46 p.m. |
| PD | Predicate disambiguation | batch_69a2f016ba5c81909825b04e7525b4ab |
completed | Feb. 28, 2026, 1:39 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.