Triple
T31074070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Třeboň |
E791902
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object |
Golden Canal
Golden Canal is a historic artificial waterway in the Třeboň region of the Czech Republic, built to manage fishponds and local water systems.
|
E1944946
|
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: Golden Canal | Statement: [Třeboň, locatedOn, Golden Canal]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Golden Canal Triple: [Třeboň, locatedOn, Golden Canal]
Generated description
Golden Canal is a historic artificial waterway in the Třeboň region of the Czech Republic, built to manage fishponds and local water systems.
Provenance (5 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f695b877c08190b6548da71d27dde7 |
completed | May 3, 2026, 12:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a292b2162d88190aaa0831a44e0b48a |
completed | June 10, 2026, 9:15 a.m. |
| NEDg | Description generation | batch_6a292dae6fc081908ca17d2de5465f6d |
completed | June 10, 2026, 9:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a292e38a7bc81908dc2261b06212031 |
completed | June 10, 2026, 9:28 a.m. |
Created at: April 29, 2026, 9:01 p.m.