Triple
T2324453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The King’s Medal |
E48254
|
entity |
| Predicate | hasReverse |
P38095
|
FINISHED |
| Object | inscription indicating merit or service |
—
|
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: inscription indicating merit or service | Statement: [The King’s Medal, hasReverse, inscription indicating merit or service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReverse Context triple: [The King’s Medal, hasReverse, inscription indicating merit or service]
-
A.
reversed
Indicates that the direction or order of a previously defined relationship or sequence between entities is inverted.
-
B.
isInverseOf
Indicates that one relation reverses the direction of another, so that if the original relates A to B, its inverse relates B to A.
-
C.
hasOppositeNumberForm
Indicates that one entity is represented by a number form that is the opposite (e.g., additive vs. subtractive, positive vs. negative, or otherwise contrastive) of the number form used to represent the other entity.
-
D.
reverseFeature
Indicates that one feature is the inverse or opposite counterpart of another feature in a given context.
-
E.
reversible
Indicates that the relationship or process can proceed in both directions, allowing a return to the original state or configuration.
- F. None of above. chosen
Provenance (4 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc685f05481909c863b29d1f6bacd |
completed | March 7, 2026, 6:32 a.m. |
| PD | Predicate disambiguation | batch_69abc5909cc48190aab257313542dc49 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc682d094819081a96ffb77c4c42a |
completed | March 7, 2026, 6:32 a.m. |
Created at: March 4, 2026, 7:50 p.m.