Triple
T23320023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivatan stone houses |
E591124
|
entity |
| Predicate | roofSecuredBy |
P151857
|
FINISHED |
| Object | wooden rafters |
—
|
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: wooden rafters | Statement: [Ivatan stone houses, roofSecuredBy, wooden rafters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofSecuredBy Context triple: [Ivatan stone houses, roofSecuredBy, wooden rafters]
-
A.
securedAgainst
Indicates that one entity is protected or safeguarded against threats, risks, or harmful actions originating from another entity or source.
-
B.
roofStatus
Indicates the current condition or state of a roof, such as whether it is intact, damaged, under repair, or replaced.
-
C.
residenceGuarded
Indicates that a residence is being actively protected or watched over, typically for security purposes.
-
D.
securedStatus
Indicates that an entity’s state, access, or data has been protected or locked down to prevent unauthorized use or modification.
-
E.
doorSafety
Indicates that a door meets specified safety conditions or standards, such as being secure, unobstructed, and compliant with safety regulations.
- F. None of above. chosen
Provenance (4 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978440888190b316664812105d60 |
completed | April 29, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
| PDg | Predicate description generation | batch_69f01d88b4ec8190a2a17a88e0eda178 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 17, 2026, 5:07 p.m.