Triple
T29482150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inpex Corporation |
E747817
|
entity |
| Predicate | hasPrimaryBusinessActivity |
P72016
|
FINISHED |
| Object | oil exploration |
—
|
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: oil exploration | Statement: [Inpex Corporation, hasPrimaryBusinessActivity, oil exploration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryBusinessActivity Context triple: [Inpex Corporation, hasPrimaryBusinessActivity, oil exploration]
-
A.
hasPrimaryBusinessLocation
Indicates that an entity’s main or principal place of business is located at a specified location.
-
B.
hasEconomicActivity
Indicates that an entity engages in, supports, or is associated with a specific type of economic activity or business operation.
-
C.
hasEntrepreneurialActivity
Indicates that an entity engages in or is associated with starting, managing, or operating business or venture-related activities.
-
D.
hasBusiness
Indicates that one entity owns, operates, or is formally associated with a business entity.
-
E.
hasPrimaryActivities
chosen
Indicates that an entity is associated with one or more main activities that define its core functions or operations.
- 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_69f0bd43ba30819095eb1cfc3adf525c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69ff7bc112088190851501fb2a16103d |
completed | May 9, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69ff7b45507c81909753866ad733601a |
completed | May 9, 2026, 6:21 p.m. |
Created at: April 28, 2026, 4:04 p.m.