Triple
T22180805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ANSI X3.74-1987 |
E548162
|
entity |
| Predicate | standardNumber |
P4626
|
FINISHED |
| Object | X3.74-1987 |
—
|
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: X3.74-1987 | Statement: [ANSI X3.74-1987, standardNumber, X3.74-1987]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: X3.74-1987 Context triple: [ANSI X3.74-1987, standardNumber, X3.74-1987]
-
A.
X-333
X-333 is a major process building at the Portsmouth Gaseous Diffusion Plant used in the large-scale enrichment of uranium.
-
B.
X-326
X-326 is a major uranium enrichment process building at the Portsmouth Gaseous Diffusion Plant in Ohio, historically used for large-scale nuclear fuel production.
-
C.
X3
chosen
X3 is the former designation of the standards body now known as INCITS, which oversees information technology standards in the United States.
-
D.
Do X3a
The Do X3a was a planned or modified version of the Dornier Do X, a massive German flying boat airliner from the interwar period.
-
E.
X38
X38 is a New York City express bus route that provides commuter service between Bath Beach in Brooklyn and Midtown Manhattan.
- 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_69e11e3d53f88190a2b690e3f25bb062 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aa4d4ac8190922b919c15623963 |
completed | April 28, 2026, 9:46 p.m. |
Created at: April 16, 2026, 8:35 p.m.