Triple
T14030682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thera eruption |
E337577
|
entity |
| Predicate | coveredSettlementWith |
P112558
|
FINISHED |
| Object | ash |
—
|
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: ash | Statement: [Thera eruption, coveredSettlementWith, ash]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coveredSettlementWith Context triple: [Thera eruption, coveredSettlementWith, ash]
-
A.
hasHumanSettlement
Indicates that a location or area contains or is the site of a human settlement, such as a town, village, or city.
-
B.
hadSettlementFeature
Indicates that a settlement possessed or contained a particular physical or infrastructural feature.
-
C.
otherSettlement
Indicates that one settlement is another, different settlement distinct from the primary or reference settlement.
-
D.
mainSettlement
Indicates that one settlement serves as the primary or most important settlement associated with a given area, region, or administrative unit.
-
E.
settlementWith
Indicates a relationship where one party reaches or maintains a settlement or agreement with another party, typically resolving a dispute or claim.
- 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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2fa9f8248190930954d609dee5f1 |
completed | April 14, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_69de05ab36b48190920efb1869bdb1fe |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de2398856c81908bed6070e4ca6ab1 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 9, 2026, 10:20 p.m.