Triple
T16535049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Street |
E401669
|
entity |
| Predicate | hasNeighbourhood |
P4813
|
FINISHED |
| Object | How Wood |
E211884
|
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: How Wood | Statement: [Park Street, hasNeighbourhood, How Wood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: How Wood Context triple: [Park Street, hasNeighbourhood, How Wood]
-
A.
How Wood
chosen
How Wood is a residential suburb and railway-served locality near St Albans in Hertfordshire, England.
-
B.
De Wood
De Wood is a specific variant or form of wood distinguished from the general category of wood materials.
-
C.
Trummen
Trummen is a lake located in or near the city of Växjö in southern Sweden.
-
D.
Weeden
Weeden is a surname most notably associated with Brandon Weeden, an American football quarterback who played in the NFL.
-
E.
Mine Woods
Mine Woods is a woodland park and popular recreational area near Bridge of Allan in central Scotland, known for its walking trails, wildlife, and scenic views.
- 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_69d88384bc30819084229e7dcdc39a41 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e345574d88819094548367bf983078 |
completed | April 18, 2026, 8:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006093244081909ae74674de966d6d |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:15 a.m.