Triple
T6073419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel of Bulgaria |
E135339
|
entity |
| Predicate | fortificationPolicy |
P172
|
FINISHED |
| Object | built and maintained strongholds in mountainous regions |
—
|
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: built and maintained strongholds in mountainous regions | Statement: [Samuel of Bulgaria, fortificationPolicy, built and maintained strongholds in mountainous regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fortificationPolicy Context triple: [Samuel of Bulgaria, fortificationPolicy, built and maintained strongholds in mountainous regions]
-
A.
fortifiedWith
Indicates that something has been strengthened, enhanced, or reinforced by the addition of a specified substance, feature, or element.
-
B.
eraPolicy
Indicates that a specific policy was in effect during a particular historical or temporal era.
-
C.
implementedPolicy
chosen
Indicates that a particular policy has been put into effect or carried out by an entity.
-
D.
supportsPolicy
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
-
E.
advancedPolicyOf
Indicates that one policy is a more developed, detailed, or progressive version of another policy.
- 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_69c00879e8048190b690717d19c5bc03 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0575b9bc08190a78b3082b9ccf00c |
completed | March 22, 2026, 8:55 p.m. |
| PD | Predicate disambiguation | batch_69c049f21fe08190995df3c5c05fb8ea |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:11 p.m.