Triple
T37793560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British American Tobacco p.l.c. |
E942144
|
entity |
| Predicate | hasISINForADR |
P6091
|
FINISHED |
| Object | US1104481072 |
—
|
LITERAL 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: US1104481072 | Statement: [British American Tobacco p.l.c., hasISINForADR, US1104481072]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasISINForADR Context triple: [British American Tobacco p.l.c., hasISINForADR, US1104481072]
-
A.
hasISIN
Indicates that a financial instrument is associated with a specific International Securities Identification Number (ISIN) that uniquely identifies it.
-
B.
isForeignIssuerADR
Indicates that an issuer is a foreign company whose shares are represented in the form of American Depositary Receipts (ADRs).
-
C.
hadISINCountryCode
Indicates that an entity was associated with a financial instrument whose ISIN code used a specific country code at some point in time.
-
D.
ISIN
chosen
Indicates that an entity is identified or associated with a specific International Securities Identification Number (ISIN).
-
E.
ISINIssuerName
Indicates that an entity is the named issuer associated with a specific ISIN (International Securities Identification Number).
- F. None of above.
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_69f76ee6f1f4819091e2cf9c9e6aee19 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.