Triple
T16718734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan (Laish) |
E406289
|
entity |
| Predicate | roleAsBoundary |
P71578
|
FINISHED |
| Object | northernmost boundary marker of Israel |
—
|
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: northernmost boundary marker of Israel | Statement: [Dan (Laish), roleAsBoundary, northernmost boundary marker of Israel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAsBoundary Context triple: [Dan (Laish), roleAsBoundary, northernmost boundary marker of Israel]
-
A.
eraOfBoundaryRole
Indicates the historical period or era during which a particular boundary role is defined, active, or relevant.
-
B.
protectsBoundary
Indicates that one entity acts to guard, defend, or maintain the limits or borders of another entity.
-
C.
adminBoundaryRelation
Indicates a relationship where one entity defines, delimits, or is associated with the administrative boundary of another entity.
-
D.
borderRegionRole
Indicates a role or function that an entity has specifically in relation to a border region or border area.
-
E.
isBoundaryFor
chosen
Indicates that one entity serves as the limiting edge, border, or enclosing extent that defines the spatial or conceptual bounds of another entity.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3865855108190bf8767b7b6c5fa10 |
completed | April 18, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:20 a.m.