Triple
T440759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahu Tongariki |
E10107
|
entity |
| Predicate | damageType |
P992
|
FINISHED |
| Object | moai toppled by tsunami |
—
|
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: moai toppled by tsunami | Statement: [Ahu Tongariki, damageType, moai toppled by tsunami]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: damageType Context triple: [Ahu Tongariki, damageType, moai toppled by tsunami]
-
A.
damagedBy
Indicates that one entity has caused harm, impairment, or deterioration to another entity.
-
B.
damagedIn
chosen
Indicates that an entity has suffered harm, impairment, or destruction as a result of a specified event, process, or condition.
-
C.
involvedPhysicalEffect
Indicates that one entity participates in causing, experiencing, or mediating a physical effect on another entity or the environment.
-
D.
fatalInjury
Indicates that an entity causes or sustains an injury that directly results in death.
-
E.
damageYear
Indicates the year in which the damage to an entity occurred or was recorded.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef2af84881909635ebbbb3465b1b |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2eddcf50c8190bfa0d1f8ee9f604a |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.