Triple
T35909504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troonstraat |
E1038565
|
entity |
| Predicate | hasConnectingSquare |
P125324
|
FINISHED |
| Object | Place du Trône / Troonplein |
E1258092
|
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: Place du Trône / Troonplein | Statement: [Troonstraat, hasConnectingSquare, Place du Trône / Troonplein]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConnectingSquare Context triple: [Troonstraat, hasConnectingSquare, Place du Trône / Troonplein]
-
A.
hasNearbySquare
Indicates that one entity has at least one square-shaped entity located close to it in space.
-
B.
citySquareConnected
chosen
Indicates that two locations are directly linked or accessible to each other via a city square.
-
C.
hasKeySquare
Indicates that one entity possesses or is associated with a specific key square that is crucial to a position or outcome.
-
D.
hasBorderConnectionPotential
Indicates that two regions or entities are positioned such that they could feasibly share a border or direct boundary under certain conditions.
-
E.
connectedByStraitTo
Indicates that one entity is geographically linked to another by a narrow body of water known as a strait.
- F. None of above.
Provenance (4 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037ce70f54819082946dad8d380825 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38ae2b4d5c8190ac0caa7f3ece9b11 |
completed | June 22, 2026, 3:38 a.m. |
| PD | Predicate disambiguation | batch_6a037a069e6c8190857b611fffb7b867 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:07 p.m.