Triple
T219887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanderbilt family |
E4189
|
entity |
| Predicate | mainBusiness |
P6749
|
FINISHED |
| Object | steamship lines |
—
|
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: steamship lines | Statement: [Vanderbilt family, mainBusiness, steamship lines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainBusiness Context triple: [Vanderbilt family, mainBusiness, steamship lines]
-
A.
businessVenture
Indicates a relationship where entities jointly engage in, operate, or are involved with a commercial or entrepreneurial undertaking.
-
B.
commercial
Indicates that one entity is engaged in a business-related or profit-oriented relationship, activity, or transaction with another entity.
-
C.
underlyingCompanyBusinessFocus
chosen
Indicates the primary industry, sector, or type of business activity that the underlying company is focused on.
-
D.
commercialPeak
Indicates the time or period when something (such as a product, artist, or business) achieves its highest level of commercial success or popularity.
-
E.
businessPartner
Indicates a formal collaborative relationship between two entities that work together in a business context, typically sharing responsibilities, risks, or benefits.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25efd0df48190b8fef4c422a1265f |
completed | Feb. 28, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69a25b54d790819093b35bd1a6f00f92 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.