Triple
T12315846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HgCdTe infrared detector |
E293596
|
entity |
| Predicate | canBeFabricatedAs |
P23101
|
FINISHED |
| Object | focal plane array |
—
|
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: focal plane array | Statement: [HgCdTe infrared detector, canBeFabricatedAs, focal plane array]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeFabricatedAs Context triple: [HgCdTe infrared detector, canBeFabricatedAs, focal plane array]
-
A.
isFabricated
Indicates that something has been artificially made, constructed, or invented rather than naturally occurring or genuinely existing.
-
B.
canBeConstructedWith
chosen
Indicates that one entity can be formed, built, or assembled using another entity as material, components, or means.
-
C.
fabricatedOn
Indicates that something was manufactured, constructed, or produced at a specific time or date.
-
D.
canBe
Indicates that one entity has the potential, permission, or capability to become, perform as, or be classified as another entity.
-
E.
canBeReconstituted
Indicates that something has the capacity to be restored or returned to a prior or functional state, typically after being separated, dissolved, or broken down.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec5be788190b82d2edc6a0f1095 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.