Triple
T6275194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Germantown, Maryland |
E140637
|
entity |
| Predicate | majorEmploymentSector |
P62538
|
FINISHED |
| Object | retail trade |
—
|
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: retail trade | Statement: [Germantown, Maryland, majorEmploymentSector, retail trade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorEmploymentSector Context triple: [Germantown, Maryland, majorEmploymentSector, retail trade]
-
A.
ownerSector
Indicates the sector or industry category to which the owner of an entity belongs.
-
B.
hasOccupationSector
chosen
Indicates that an entity’s occupation belongs to or is categorized within a particular economic or professional sector.
-
C.
professionalSector
Indicates the industry or field in which an entity conducts its professional or occupational activities.
-
D.
employerType
Indicates the classification or category of an employer in relation to the entity (e.g., public, private, nonprofit, self-employed).
-
E.
employerFocus
Indicates that an employer directs particular attention, resources, or priority toward a specific subject, group, or area.
- 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_69c008cc158881908df6ec94a911c736 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063c170bc8190933e2fd5c9fef783 |
completed | March 22, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69c05606fb50819082d1a5a91e5030b6 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:25 p.m.