Triple
T35915893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Konwinski |
E1038747
|
entity |
| Predicate | earlyContributorTo |
P30146
|
FINISHED |
| Object | Apache Spark |
—
|
NE NERFINISHED |
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: Apache Spark | Statement: [Andy Konwinski, earlyContributorTo, Apache Spark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlyContributorTo Context triple: [Andy Konwinski, earlyContributorTo, Apache Spark]
-
A.
firstContributor
Indicates that the subject is the earliest or initial contributor to the object within a given context or project.
-
B.
pioneeredIn
Indicates that an entity was among the first to develop, introduce, or significantly advance something within a particular field, domain, or location.
-
C.
pioneerWorkOf
Indicates that one entity is the original, groundbreaking work or foundational contribution created by another entity.
-
D.
pioneerOf
Indicates that an entity was among the first to develop, introduce, or significantly advance another entity, concept, or practice.
-
E.
hasContributionFrom
chosen
Indicates that something (such as a work, project, or outcome) is created, influenced, or supported in part by a specified contributor.
- 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_69f76e2320748190b7f5c4750d0cd0d3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2c771108190adeec151daad5dab |
completed | May 3, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bad2e88190963ab4ee5d4f2038 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:07 p.m.