Triple
T16736467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uzziah |
E406729
|
entity |
| Predicate | residenceAfterLeprosy |
P124448
|
FINISHED |
| Object | separate house |
—
|
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: separate house | Statement: [Uzziah, residenceAfterLeprosy, separate house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residenceAfterLeprosy Context triple: [Uzziah, residenceAfterLeprosy, separate house]
-
A.
residenceAfterService
Indicates that an entity’s place of residence is located or established after completing a specified period of service (such as military or public service).
-
B.
residenceAfterRelease
Indicates the place where an individual lives or is located following their release from a prior confinement, custody, or institutional stay.
-
C.
residenceBeforePlague
Indicates that one entity lived or was located in a particular place prior to the occurrence of a specified plague.
-
D.
residenceAfterTransformation
Indicates the place where an entity lives or is located after undergoing a specified transformation or change.
-
E.
residenceAfterFlood
Indicates that an entity’s place of residence is the one occupied after a flood event has occurred.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e39c3a86848190a03f243dd1bdb899 |
completed | April 18, 2026, 2:59 p.m. |
| PD | Predicate disambiguation | batch_69e319c807788190901250ab6e0ca55f |
completed | April 18, 2026, 5:42 a.m. |
| PDg | Predicate description generation | batch_69e326b9e84881909a9166e65bd850d6 |
completed | April 18, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:20 a.m.