Triple
T37614369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngāti Rangitihi |
E935876
|
entity |
| Predicate | hasAncestralLake |
P194644
|
FINISHED |
| Object | Lake Tarawera |
—
|
NE NERFINISHED |
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: Lake Tarawera | Statement: [Ngāti Rangitihi, hasAncestralLake, Lake Tarawera]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAncestralLake Context triple: [Ngāti Rangitihi, hasAncestralLake, Lake Tarawera]
-
A.
hasAncestralRiver
Indicates that an entity is associated with or originates from a river regarded as its ancestral or traditional source.
-
B.
consideredAncientLake
Indicates that a body of water is regarded as an ancient lake, typically having existed continuously for a very long geological timespan.
-
C.
hasAncestralIsland
Indicates that an entity has a specific island from which its ancestors originated or to which its lineage is historically tied.
-
D.
hasMajorLake
Indicates that a geographic region or area contains at least one significant lake within its boundaries.
-
E.
hasLakes
Indicates that one entity possesses, contains, or is characterized by the presence of one or more lakes.
- 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_69f76ed16b748190ad6add183b1be688 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd7e364a648190a1e9e1d9fc76e99e |
completed | May 8, 2026, 6:09 a.m. |
| PD | Predicate disambiguation | batch_69fd7bb547608190a3b04dddbca6b8bc |
completed | May 8, 2026, 5:59 a.m. |
| PDg | Predicate description generation | batch_69fd7e35967081909f8bc8389d976ffd |
completed | May 8, 2026, 6:09 a.m. |
Created at: May 3, 2026, 4:18 p.m.