Triple
T19687131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loughinisland massacre |
E472739
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Heights Bar |
—
|
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: Heights Bar | Statement: [Loughinisland massacre, location, Heights Bar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heights Bar Context triple: [Loughinisland massacre, location, Heights Bar]
-
A.
The Heights Bar
chosen
The Heights Bar is a public house in Loughinisland, County Down, Northern Ireland, best known as the site of the 1994 sectarian Loughinisland massacre.
-
B.
Tower Bar
Tower Bar is an upscale, classic Hollywood lounge and restaurant located inside the Sunset Tower Hotel on the Sunset Strip in West Hollywood.
-
C.
Harwood Bar
Harwood Bar is a locality or neighbourhood situated near the town of Great Harwood in Lancashire, England.
-
D.
The Bar
The Bar is a Spanish thriller film directed by Álex de la Iglesia that follows a group of strangers trapped in a bar after a mysterious sniper attack outside.
-
E.
The Rooster Bar
The Rooster Bar is a legal thriller novel by bestselling American author John Grisham that follows law students entangled in a predatory student-loan and for-profit law school scheme.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6420c3f50819082b64b1fa4335e56 |
completed | April 20, 2026, 3:11 p.m. |
Created at: April 10, 2026, 1:45 p.m.