Triple
T5987719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harray Hills |
E133268
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Harray |
E512671
|
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: Harray | Statement: [Harray Hills, hasNearbySettlement, Harray]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harray Context triple: [Harray Hills, hasNearbySettlement, Harray]
-
A.
Harray
chosen
Harray is a rural parish on Mainland Orkney in Scotland, characterized by open moorland, lochs, and traditional agricultural landscapes.
-
B.
Harold Saxon
Harold Saxon is an alias used by the Master, a recurring Time Lord villain in the Doctor Who television series, during his tenure as a manipulative British politician.
-
C.
Hugh
Hugh is a masculine given name of Germanic origin, commonly used in English-speaking countries.
-
D.
Hannington
Hannington is a small rural village in Wiltshire, England, known for its traditional English countryside setting and historic character.
-
E.
Stuart
Stuart is the royal dynasty that ruled Scotland and later England and Ireland, most famously associated with monarchs such as James I and Charles I.
- 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_69c0087010d081908bb8142342d63330 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04dc38a308190a368c5c787a5fc64 |
completed | March 22, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1135e653481909869094063d31605 |
completed | March 23, 2026, 10:18 a.m. |
Created at: March 22, 2026, 4:04 p.m.