Triple
T18561874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barter Island |
E453659
|
entity |
| Predicate | hasIATAcode |
P2569
|
FINISHED |
| Object | BTI |
—
|
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: BTI | Statement: [Barter Island, hasIATAcode, BTI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BTI Context triple: [Barter Island, hasIATAcode, BTI]
-
A.
BTI
BTI is the stock ticker symbol for British American Tobacco p.l.c., one of the world’s largest multinational tobacco companies.
-
B.
BTI
chosen
BTI is the IATA airport code for Kaktovik Airport in Alaska, United States.
-
C.
BTI
BTI (Barisan Tani Indonesia) was the mass peasant organization affiliated with the Indonesian Communist Party (PKI), active in agrarian struggles and land reform campaigns in mid-20th-century Indonesia.
-
D.
HBTI
HBTI is a renowned engineering and technology university located in Kanpur, India, known for its strong academic programs and research in technical fields.
-
E.
BIPT
BIPT is a specialized university in Beijing focused on petrochemical engineering and related applied sciences and technologies.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5380a46f08190afe7ca2ddfe209d5 |
completed | April 19, 2026, 8:16 p.m. |
Created at: April 10, 2026, 11:42 a.m.