Triple
T27629143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stanimaka |
E696289
|
entity |
| Predicate | hasMedievalFortress |
P95256
|
FINISHED |
| Object | Asen’s Fortress |
E1398749
|
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: Asen’s Fortress | Statement: [Stanimaka, hasMedievalFortress, Asen’s Fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMedievalFortress Context triple: [Stanimaka, hasMedievalFortress, Asen’s Fortress]
-
A.
hasMedievalBuilding
Indicates that one entity possesses, contains, or includes a building dating from the medieval period.
-
B.
hasMedievalVillageCenter
Indicates that an entity includes or is associated with a central area characteristic of a medieval village, such as its main hub of settlement or activity.
-
C.
hasMedievalCityCenter
Indicates that a place possesses a historically preserved or identifiable city center originating from the medieval period.
-
D.
hasFamousCastle
Indicates that an entity possesses or is the location of a castle that is widely recognized or renowned.
-
E.
containsHistoricFort
chosen
Indicates that a place or area includes within its boundaries a historic fort.
- 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_69ef59092c8881908114ad184248cc46 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f78fd5a6388190bfda4bbb2e222e5b |
completed | May 3, 2026, 6:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12da88358881908eec45d4adc4ed07 |
completed | May 24, 2026, 11:01 a.m. |
| PD | Predicate disambiguation | batch_69f78e2ac3fc819081a45c6841375c8d |
completed | May 3, 2026, 6:04 p.m. |
Created at: April 27, 2026, 2:20 p.m.