Triple
T28369985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Lau Spreading Center |
E718598
|
entity |
| Predicate | isBackArcTo |
P164435
|
FINISHED |
| Object | Tonga volcanic arc |
—
|
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: Tonga volcanic arc | Statement: [Central Lau Spreading Center, isBackArcTo, Tonga volcanic arc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBackArcTo Context triple: [Central Lau Spreading Center, isBackArcTo, Tonga volcanic arc]
-
A.
hasArc
Indicates that there is a directed connection or edge from one entity to another, often representing a link in a graph or network.
-
B.
formsArcOf
Indicates that one entity curves around or spans between points so as to create an arc in relation to another entity.
-
C.
undergoesArc
Indicates that an entity is subjected to or experiences a specific arc process, transformation, or phase.
-
D.
adjacentIslandArc
Indicates that one island arc is directly next to or bordering another island arc in geographic space.
-
E.
hasArcType
Indicates that one entity is associated with, or characterized by, a specific type or category of arc.
- 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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5986bc81908bcab5bd97178059 |
completed | May 2, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
| PDg | Predicate description generation | batch_69f64bca8574819095e081cbb7e2f369 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 28, 2026, 12:58 a.m.