Triple
T12539044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harkstead |
E299787
|
entity |
| Predicate | civilParishOf |
P9019
|
FINISHED |
| Object | Harkstead |
E299787
|
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: Harkstead | Statement: [Harkstead, civilParishOf, Harkstead]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harkstead Context triple: [Harkstead, civilParishOf, Harkstead]
-
A.
Harkstead
chosen
Harkstead is a small rural village and civil parish in Suffolk, England, situated near the River Stour on the Shotley Peninsula.
-
B.
Willowbridge
Willowbridge is a small rural settlement located within New Zealand’s Waimate District in the South Island.
-
C.
Lakefield
Lakefield is a small village in Ontario, Canada, known for its scenic setting along the Otonabee River and its historic, cottage-country character.
-
D.
Halstead
Halstead is a historic market town in the county of Essex in the East of England.
-
E.
Rhawnhurst
Rhawnhurst is a residential neighborhood in the Northeast section of Philadelphia, Pennsylvania, known for its post-World War II housing and suburban character.
- 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_69d6ada707008190aaec1238117c9379 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d9546ebf508190ae54857e4289c6e4 |
completed | April 10, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6557cb180819083ee10708320199e |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 8, 2026, 9:57 p.m.