Triple
T17305577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portal |
E420153
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Portel |
E380685
|
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: Portel | Statement: [Portal, hasVariant, Portel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Portel Context triple: [Portal, hasVariant, Portel]
-
A.
Portel
chosen
Portel is a municipality and town in Portugal’s Alentejo region, known for its historic castle and rural landscapes.
-
B.
Porta Faul
Porta Faul is a historic city gate in Viterbo, Italy, notable as part of the town’s medieval defensive walls.
-
C.
Portikus
Portikus is a contemporary art exhibition space in Frankfurt am Main known for its experimental programming and focus on international avant-garde artists.
-
D.
Las Portelas
Las Portelas is a small rural settlement located within Tenerife’s Teno Rural Park in the Canary Islands, Spain.
-
E.
La Portellada
La Portellada is a small rural municipality in the province of Teruel, Aragon, Spain, known for its traditional agriculture and scenic Matarraña (Matarranya) landscape.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e438ff3ee08190ab4c44a22f86b38b |
completed | April 19, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180de8340819081eae1104d705de0 |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:43 a.m.