Triple
T22766231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moltke |
E563133
|
entity |
| Predicate | hasEponymCategory |
P149643
|
FINISHED |
| Object | person (military figure) |
—
|
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: person (military figure) | Statement: [Moltke, hasEponymCategory, person (military figure)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEponymCategory Context triple: [Moltke, hasEponymCategory, person (military figure)]
-
A.
hasEponymType
Indicates that something is associated with or classified by a particular type of eponym (a name derived from a person).
-
B.
hasEponymConnectionTo
Indicates that one entity is named after, derived from, or otherwise linguistically or honorifically connected to another entity as its eponym.
-
C.
hasEponymFamilyRelation
Indicates that one entity is named after another entity to which it is related by family or kinship.
-
D.
isNamedForEponymRole
Indicates that one entity bears a name derived from another entity that serves as its eponym or namesake.
-
E.
hasEponymField
Indicates that something (such as a concept, object, or entity) is named after a particular person or eponym.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a80e2688190b76844c408929d32 |
completed | April 29, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
| PDg | Predicate description generation | batch_69eeeb5681f88190821129ced752f190 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 17, 2026, 3:26 p.m.