Triple
T17426703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Small Carry-on Impactor |
E423755
|
entity |
| Predicate | projectileMaterial |
P618
|
FINISHED |
| Object | copper |
—
|
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: copper | Statement: [Small Carry-on Impactor, projectileMaterial, copper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectileMaterial Context triple: [Small Carry-on Impactor, projectileMaterial, copper]
-
A.
involvesProjectile
Indicates that the action or event includes the use, presence, or motion of a projectile as a key component of the interaction between entities.
-
B.
exampleMaterial
Indicates that something serves as a representative or illustrative material or sample of something else.
-
C.
pylonMaterial
Indicates that a pylon is made of, constructed from, or primarily composed of a specified material.
-
D.
material
chosen
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
-
E.
materialOptions
Indicates that there are one or more possible materials that can be chosen or applied in relation to a given 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e448fcbf54819091babed0b9b05716 |
completed | April 19, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69e3b030eac481909b8402719cc3102e |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:46 a.m.