Triple
T9088426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wm. Rogers |
E217815
|
entity |
| Predicate | collectingDomain |
P51039
|
FINISHED |
| Object | vintage silverplate flatware |
—
|
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: vintage silverplate flatware | Statement: [Wm. Rogers, collectingDomain, vintage silverplate flatware]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectingDomain Context triple: [Wm. Rogers, collectingDomain, vintage silverplate flatware]
-
A.
collectingArea
Indicates the total surface area over which something (typically a device or system) gathers or receives a substance, signal, or resource.
-
B.
collects
Indicates that one entity gathers, accumulates, or brings together one or more other entities into its possession or control.
-
C.
collectorInterest
chosen
Indicates that one entity has a special interest in acquiring, owning, or seeking out another entity as part of a collection.
-
D.
domainOfq
Indicates that a given entity serves as the domain (set of permissible inputs or arguments) for the quantity or relation denoted by q.
-
E.
collectionBuiltAround
Indicates that a collection is organized, structured, or conceptually centered around a particular core item, theme, or entity.
- 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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9657d48081909e0ae0f1fa8ff599 |
completed | April 1, 2026, 3:51 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:14 p.m.