Triple
T27343556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LI-900 silica tiles |
E684171
|
entity |
| Predicate | attachmentFeature |
P93025
|
FINISHED |
| Object | strain isolation pad between tile and structure |
—
|
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: strain isolation pad between tile and structure | Statement: [LI-900 silica tiles, attachmentFeature, strain isolation pad between tile and structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attachmentFeature Context triple: [LI-900 silica tiles, attachmentFeature, strain isolation pad between tile and structure]
-
A.
attachedTo
Indicates that one entity is physically or logically fastened, connected, or joined to another entity.
-
B.
attachmentType
chosen
Indicates the specific kind or category of attachment that relates one entity to another.
-
C.
annexDFeature
Indicates that one entity includes or incorporates another entity as a feature defined or specified in Annex D.
-
D.
auxiliaryFeature
Indicates that one feature functions as a secondary or supporting capability to another primary feature.
-
E.
recognizedFeature
Indicates that a particular feature has been identified and acknowledged as present or valid in relation to an 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62ba0fedc8190b63a546f7d893676 |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:44 a.m.