Triple
T36973938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Good Delivery gold bars |
E914645
|
entity |
| Predicate | hasFaceMarking |
P125456
|
FINISHED |
| Object | refiner’s assay mark |
—
|
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: refiner’s assay mark | Statement: [Good Delivery gold bars, hasFaceMarking, refiner’s assay mark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFaceMarking Context triple: [Good Delivery gold bars, hasFaceMarking, refiner’s assay mark]
-
A.
hasFieldMarkingsFor
Indicates that one entity includes or displays field markings that are intended or suitable for use by another entity.
-
B.
facialMarkings
chosen
Indicates that one entity has distinctive marks, patterns, or features on its face in relation to another entity or context.
-
C.
hasHeadMarkings
Indicates that an entity possesses distinct markings or patterns on its head.
-
D.
hasFacePaintColor
Indicates that an entity’s face paint is of a specified color.
-
E.
eggMarkings
Indicates that one entity bears or displays specific markings or patterns on its eggs in relation to another entity or context.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe831c97c88190b27ecf100e25c2a0 |
completed | May 9, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_69fe7f1b92648190b14e56bcaee5d0ca |
completed | May 9, 2026, 12:26 a.m. |
Created at: May 3, 2026, 4:14 p.m.