Triple
T37482410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battenberg–Mountbatten line |
E931444
|
entity |
| Predicate | hasMemberFamilyName |
P77449
|
FINISHED |
| Object | Battenberg |
—
|
NE NERFINISHED |
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: Battenberg | Statement: [Battenberg–Mountbatten line, hasMemberFamilyName, Battenberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMemberFamilyName Context triple: [Battenberg–Mountbatten line, hasMemberFamilyName, Battenberg]
-
A.
hasFamilyNameOf
Indicates that one entity bears or uses the same family name (surname) as another entity.
-
B.
hasNameInFamily
Indicates that an entity is known or referred to by a particular name within the context of a specific family or familial group.
-
C.
containsFamily
Indicates that one entity includes or encompasses members of a particular family group within it.
-
D.
familyNameOfMembers
Indicates that the specified family name is shared by the members of a given group or family.
-
E.
hasMemberBySurname
chosen
Indicates that a group or collection includes a member identified by a specific surname.
- 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_69f76ec382248190b47844df596123c6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff9a25407c81909faa86e72a7a9d17 |
completed | May 9, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69ff99c613688190a03b2f93d5ccad2b |
completed | May 9, 2026, 8:32 p.m. |
Created at: May 3, 2026, 4:17 p.m.