Triple
T19966609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellaghy |
E479950
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Toome |
—
|
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: Toome | Statement: [Bellaghy, locatedNear, Toome]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toome Context triple: [Bellaghy, locatedNear, Toome]
-
A.
Toome
chosen
Toome is a small village in County Antrim, Northern Ireland, known for its location at the northern end of Lough Neagh and its historic bridge and eel fishing industry.
-
B.
Valga
Valga is a small border town in southern Estonia known for forming a twin city with Valka in Latvia.
-
C.
Tammneeme
Tammneeme is a coastal village in northern Estonia known for its seaside location on the Viimsi Peninsula near Tallinn.
-
D.
Heltermaa
Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
-
E.
Kraainem
Kraainem is a Dutch- and French-speaking suburban municipality on the eastern edge of Brussels in the Flemish Brabant province of Belgium.
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65bc5e41881908c1e8867820f1c0c |
completed | April 20, 2026, 5 p.m. |
Created at: April 10, 2026, 1:54 p.m.