Triple
T4483394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tino Sehgal |
E100181
|
entity |
| Predicate | marketPractice |
P40560
|
FINISHED |
| Object | sells works through verbal agreements |
—
|
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: sells works through verbal agreements | Statement: [Tino Sehgal, marketPractice, sells works through verbal agreements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marketPractice Context triple: [Tino Sehgal, marketPractice, sells works through verbal agreements]
-
A.
market
Indicates the act of promoting, advertising, or selling a product, service, or idea to potential buyers or target audiences.
-
B.
businessPractice
chosen
Indicates a relationship where an entity engages in, follows, or is characterized by a particular method, procedure, or customary way of conducting business activities.
-
C.
marketContext
Indicates the broader economic, competitive, and situational conditions under which a product, service, or transaction is positioned or evaluated.
-
D.
marketUse
Indicates that something is used, applied, or exploited within a market or commercial context.
-
E.
marketForm
Indicates the type or structure of the market in which an entity operates or a transaction occurs.
- 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_69b34553cbe48190afa8ac1cac285b86 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35728ed508190ba0e882fa62d8848 |
completed | March 13, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69b3563d63008190816e37027e761375 |
completed | March 13, 2026, 12:11 a.m. |
Created at: March 12, 2026, 11:36 p.m.