Triple
T590535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Book Store |
E17256
|
entity |
| Predicate | hasCustomerBase |
P2823
|
FINISHED |
| Object | students |
—
|
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: students | Statement: [Harvard Book Store, hasCustomerBase, students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCustomerBase Context triple: [Harvard Book Store, hasCustomerBase, students]
-
A.
hasMembershipBase
Indicates that an entity possesses or is associated with a foundational group or set of members that form its membership base.
-
B.
hasVolunteerBase
Indicates that an entity maintains or relies on a group of volunteers as a foundational support resource.
-
C.
hasMarketParticipants
chosen
Indicates that a market or trading venue involves or is associated with specific participating entities (such as buyers, sellers, or intermediaries).
-
D.
majorCustomer
Indicates that one entity is a primary or high-value customer of another entity, typically contributing a significant portion of business or revenue.
-
E.
hasTenants
Indicates that an entity occupies or rents space from another entity as its tenant.
- 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_69a49379d09c8190ac7e00b24e2810b1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49bb8ff0081909cd53d88930e2693 |
completed | March 1, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69a494cc13988190892ca10bd7ae9f09 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.