Triple
T2176703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Cross with Collar |
E48544
|
entity |
| Predicate | collarMaterial |
P1272
|
FINISHED |
| Object | precious metal |
—
|
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: precious metal | Statement: [Grand Cross with Collar, collarMaterial, precious metal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collarMaterial Context triple: [Grand Cross with Collar, collarMaterial, precious metal]
-
A.
supporterCollar
Indicates that one entity serves as a collar-like structural element that supports or stabilizes another entity.
-
B.
associatedMetal
Indicates a relationship where one entity is linked or connected to a particular metal, such as by composition, usage, origin, or symbolic association.
-
C.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
D.
hasClasps
Indicates that one entity is equipped with or features clasps that fasten, secure, or attach it to another entity or its parts.
-
E.
wornAround
Indicates that one entity is physically worn encircling or surrounding another entity (e.g., around a body part or object).
- 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_69a88aa3faa48190995b233af6525815 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc4358fc88190a6f556c2de9fef8c |
completed | March 7, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69abbda0ec948190be88c1243d81a423 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.