Triple
T29793466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FK Srem |
E756475
|
entity |
| Predicate | hasHomeStadium |
P890
|
FINISHED |
| Object |
Stadion FK Srem
Stadion FK Srem is a football stadium in Sremska Mitrovica, Serbia, serving as the home ground of the FK Srem football club.
|
E1883771
|
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: Stadion FK Srem | Statement: [FK Srem, hasHomeStadium, Stadion FK Srem]
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: Stadion FK Srem Triple: [FK Srem, hasHomeStadium, Stadion FK Srem]
Generated description
Stadion FK Srem is a football stadium in Sremska Mitrovica, Serbia, serving as the home ground of the FK Srem football club.
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_69f22454583081908927516cb9938d1d |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f674e4bb8c8190baf5c9fbfe45e4e1 |
completed | May 2, 2026, 10:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a26c90a7bac8190a9c0317842364d01 |
completed | June 8, 2026, 1:52 p.m. |
| NEDg | Description generation | batch_6a26d44f8184819089648aaf5fea3616 |
completed | June 8, 2026, 2:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a26d50e86a08190a4d70c2b0168a145 |
completed | June 8, 2026, 2:43 p.m. |
Created at: April 29, 2026, 5:13 p.m.