Triple
T16335047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thirlestane Castle |
E396655
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Borders |
E86254
|
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: Borders | Statement: [Thirlestane Castle, locatedIn, Borders]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Borders Context triple: [Thirlestane Castle, locatedIn, Borders]
-
A.
Borders
Borders is a surname of English origin borne by various individuals, including the former professional baseball player Pat Borders.
-
B.
Borders
"Borders" is a politically charged 2015 song by British-Sri Lankan artist M.I.A. that critiques global immigration policies and the treatment of refugees.
-
C.
Borders
chosen
Borders is a rural region in southern Scotland known for its rolling hills, historic abbeys, and small market towns near the English border.
-
D.
Border
"Border" is a 1997 Indian war drama film directed by J. P. Dutta that depicts the Battle of Longewala during the Indo-Pakistani War of 1971.
-
E.
Border Lines
Border Lines is a thematic section of the Zurich Film Festival that showcases films exploring political, social, and humanitarian conflicts and the borders—literal and metaphorical—that define them.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e29db88190936a07deb5b1c1e3 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0026193a3c81909c640426ab798c1c |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.