Triple
T25975534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paseo de Recoletos |
E645925
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object |
Recoletos convent
Recoletos convent was a former Augustinian Recollect monastery in Madrid whose presence gave its name to the surrounding Paseo de Recoletos area.
|
E1705611
|
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: Recoletos convent | Statement: [Paseo de Recoletos, namedAfter, Recoletos convent]
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: Recoletos convent Triple: [Paseo de Recoletos, namedAfter, Recoletos convent]
Generated description
Recoletos convent was a former Augustinian Recollect monastery in Madrid whose presence gave its name to the surrounding Paseo de Recoletos area.
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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f60508b04c8190af744b1dbeffe4b4 |
completed | May 2, 2026, 2:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a11078bf720819080bd5f89b5b7904b |
completed | May 23, 2026, 1:49 a.m. |
| NEDg | Description generation | batch_6a11082bcf9c8190a80f0ed23b79a823 |
completed | May 23, 2026, 1:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a110c2ac828819088a7a9feb579e6e6 |
completed | May 23, 2026, 2:08 a.m. |
Created at: April 22, 2026, 8:51 a.m.