Triple
T13615324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NAICS codes |
E325296
|
entity |
| Predicate | thirdLevelName |
P18792
|
FINISHED |
| Object | industry group |
—
|
LITERAL 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: industry group | Statement: [NAICS codes, thirdLevelName, industry group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdLevelName Context triple: [NAICS codes, thirdLevelName, industry group]
-
A.
thirdTier
chosen
Indicates that an entity occupies a third level or rank within a hierarchical structure or classification.
-
B.
thirdStageName
Indicates that an entity has a third stage in a sequence or process, and this predicate specifies the name of that third stage.
-
C.
thirdLevelRepresents
Indicates that something serves as a representation or abstraction of another thing at a third level in a hierarchical or multi-level representational structure.
-
D.
thirdWord
Indicates that one entity is the third word in sequence within another entity (such as a text or phrase).
-
E.
thirdUnitName
Indicates that the predicate specifies the name of the third unit in an ordered sequence or grouping of units.
- 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_69d8076aae28819092cf636190ee5529 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbb9ee3f081909056dc1a92c40b7a |
completed | April 12, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69dbae1b3ee481909bd43ded6227a3e5 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:50 p.m.