Triple
T10377899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NSRS |
E244553
|
entity |
| Predicate | administeredBy |
P86
|
FINISHED |
| Object | NGS |
E50887
|
NE 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: NGS | Statement: [NSRS, administeredBy, NGS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NGS Context triple: [NSRS, administeredBy, NGS]
-
A.
NGS
chosen
NGS is the National Geodetic Survey, the U.S. federal agency responsible for defining and managing the national coordinate system used for mapping, navigation, and surveying.
-
B.
NGS
NGS is the abbreviation for the Nasdaq Global Select Market, a premier tier of the Nasdaq stock exchange that lists companies meeting the highest financial and corporate governance standards.
-
C.
Ion Torrent
Ion Torrent is a DNA sequencing technology platform known for its semiconductor-based sequencing method that detects hydrogen ions released during nucleotide incorporation.
-
D.
Nebula Genomics
Nebula Genomics is a personal genomics company that offers whole-genome sequencing and analysis with a focus on privacy-preserving, blockchain-based data sharing.
-
E.
Edico Genome
Edico Genome was a biotechnology company specializing in high-speed genomic data analysis through its DRAGEN bio-IT platform and FPGA-based acceleration technology.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e98f312481909f7276fc3762d7bc |
completed | April 7, 2026, 11:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7957e52108190a8d262b30a7d2780 |
completed | April 9, 2026, 12:03 p.m. |
Created at: April 6, 2026, 12:03 p.m.