Triple
T15636847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gdańsk Old Town |
E375966
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Green Gate |
E101619
|
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: Green Gate | Statement: [Gdańsk Old Town, hasLandmark, Green Gate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Gate Context triple: [Gdańsk Old Town, hasLandmark, Green Gate]
-
A.
Green Gate
Green Gate is a historic city gate and prominent architectural landmark in the Czech city of Pardubice.
-
B.
Green Gate
chosen
Green Gate is a historic Renaissance-style city gate in Gdańsk, Poland, forming a grand riverside entrance between the Long Market and the Motława River.
-
C.
Green Gate
Green Gate is one of the ornately decorated, color-themed doorways of Jaipur’s City Palace courtyard, known for its vivid green hues and intricate Rajasthani design.
-
D.
Priory Gardens
Priory Gardens is a historic riverside garden in Ware, Hertfordshire, known for its landscaped grounds surrounding the medieval Ware Priory.
-
E.
Priory Gardens
Priory Gardens is a public park in Orpington, Kent, England, known for its landscaped grounds, ornamental lake, and the historic Priory building at its edge.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04eba51f08190ac5d9de7fc89405a |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f4923ac8190a03fe1f2c878c27e |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:14 a.m.