Triple
T32582764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Order of the Lion |
E832833
|
entity |
| Predicate | originallyLinkedTo |
P32436
|
FINISHED |
| Object | Congo Free State |
E102002
|
NE 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: Congo Free State | Statement: [Royal Order of the Lion, originallyLinkedTo, Congo Free State]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originallyLinkedTo Context triple: [Royal Order of the Lion, originallyLinkedTo, Congo Free State]
-
A.
originallyAssociatedWith
chosen
Indicates that an entity was first linked, connected, or affiliated with another entity before any later changes in association.
-
B.
currentlyLinkedTo
Indicates that one entity is at this moment connected or associated with another entity in an ongoing relationship or linkage.
-
C.
hasBeenLinkedTo
Indicates that an entity has been associated or connected with another entity, often suggesting a reported or inferred relationship between them.
-
D.
originallyBy
Indicates that one entity is the original creator, author, or source of another entity.
-
E.
originAssociatedWith
Indicates a relationship where an entity is connected to, derived from, or influenced by a particular origin, source, or point of beginning.
- F. None of above.
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_69f349289adc81909f4374a58ec35a39 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01b935e3948190a7af37b07938d618 |
completed | May 11, 2026, 11:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a348609b6b8819083ab1db2652aaee1 |
completed | June 18, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_6a01b8d198b48190b01e16ac9ce7e7bd |
completed | May 11, 2026, 11:09 a.m. |
Created at: May 1, 2026, 1:04 a.m.