Triple
T19704149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Jones |
E473167
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Science Inc. |
—
|
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: Science Inc. | Statement: [Mike Jones, employer, Science Inc.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Science Inc. Context triple: [Mike Jones, employer, Science Inc.]
-
A.
Science Inc.
chosen
Science Inc. is a consumer products company known for developing and marketing innovative, data-driven brands such as the meal replacement drink Soylent.
-
B.
City of Science
City of Science is an honorary title awarded to Darmstadt in recognition of its prominent role as a center for scientific research, education, and innovation.
-
C.
Universcience
Universcience is a French public institution that manages major science museums and centers in Paris, promoting scientific culture and education to a broad audience.
-
D.
Mr. Science
Mr. Science is a symbolic figure representing the ideals of modern scientific rationality and progress that Chinese intellectuals championed during the May Fourth Movement.
-
E.
Scientia
Scientia is a Latin word meaning "knowledge," commonly used in academic and scholarly mottos and contexts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b8707081908fbf96c989d2d52d |
completed | April 20, 2026, 3:14 p.m. |
Created at: April 10, 2026, 1:46 p.m.