Triple
T20352187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leo II |
E496038
|
entity |
| Predicate | catalog |
P20407
|
FINISHED |
| Object | PGC |
—
|
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: PGC | Statement: [Leo II, catalog, PGC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PGC Context triple: [Leo II, catalog, PGC]
-
A.
PGC
chosen
PGC is an astronomical catalog that systematically lists and provides data on galaxies, including objects like the Leo II Dwarf Galaxy.
-
B.
PGCRL
PGCRL is a major pediatric research facility in Toronto that houses scientists and clinicians focused on advancing child health and medical innovation.
-
C.
PGR
PGR is the stock ticker symbol for The Progressive Corporation, a major U.S. insurance company best known for its auto insurance offerings.
-
D.
PGS
PGS stands for Prompt Global Strike, a U.S. military concept aimed at enabling rapid, precision conventional strikes anywhere in the world within a short time frame.
-
E.
PGZ
PGZ is a major Polish state-owned defense holding company that consolidates much of Poland’s arms and military equipment industry.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67850ace48190b19aff5780fef7e8 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.