Triple
T20006821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Behind Her Eyes |
E494480
|
entity |
| Predicate | filmingLocation |
P40
|
FINISHED |
| Object | Scotland |
—
|
NE NERFINISHED |
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: Scotland | Statement: [Behind Her Eyes, filmingLocation, Scotland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scotland Context triple: [Behind Her Eyes, filmingLocation, Scotland]
-
A.
Scotland
chosen
Scotland is a country in the northern part of the United Kingdom, known for its distinct cultural heritage, historic castles, rugged landscapes, and major cities such as Edinburgh and Glasgow.
-
B.
Scotland
Scotland is a small town located in Telfair County in the U.S. state of Georgia.
-
C.
Mainland Scotland
Mainland Scotland is the northern part of Great Britain, encompassing Scotland’s largest cities, diverse landscapes from Highlands to Lowlands, and serving as the country’s principal economic and cultural heartland.
-
D.
Escosse
Escosse is a small commune in the Ariège department of southwestern France, situated within the arrondissement of Pamiers.
-
E.
Schokland
Schokland is a former island in the Dutch Zuiderzee, now a UNESCO World Heritage Site known for its archaeological remains and history of land reclamation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a648a88190853ee741edcf6ca2 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:33 p.m.