Triple
T27343528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LI-900 silica tiles |
E684171
|
entity |
| Predicate | compositionByWeight |
P146332
|
FINISHED |
| Object | approximately 90 percent air |
—
|
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: approximately 90 percent air | Statement: [LI-900 silica tiles, compositionByWeight, approximately 90 percent air]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compositionByWeight Context triple: [LI-900 silica tiles, compositionByWeight, approximately 90 percent air]
-
A.
compositionFrom
chosen
Indicates that something is formed or made up from specified constituent parts or materials.
-
B.
composedBy
Indicates that one entity is the creator or author of a musical or artistic work associated with another entity.
-
C.
fractionHeavierElementsByMass
Indicates the proportion of an object's total mass that is contributed by elements heavier than a specified reference element (often hydrogen or helium).
-
D.
compositionVariesBy
Indicates that the composition of something differs depending on a specified factor, condition, or context.
-
E.
composedTo
Indicates that one entity created or authored another entity, typically a work such as a piece of music, writing, or art.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6a28c7c148190bfc980aad9f678ca |
completed | May 3, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69f69fe1e3c88190830bb2e9f407357e |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 27, 2026, 11:44 a.m.