Triple
T978201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Hanshin earthquake |
E21104
|
entity |
| Predicate | primaryDamageType |
P22116
|
FINISHED |
| Object | structural collapse |
—
|
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: structural collapse | Statement: [Great Hanshin earthquake, primaryDamageType, structural collapse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDamageType Context triple: [Great Hanshin earthquake, primaryDamageType, structural collapse]
-
A.
primaryEffect
Indicates the main direct outcome or consequence that results from a given cause, action, or condition.
-
B.
primaryForce
Indicates that one entity serves as the main or dominant force acting upon, influencing, or driving another entity or process.
-
C.
primaryMode
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
D.
primaryTargetType
Indicates the main category or type of entity that is the principal focus or intended recipient of an action, effect, or operation.
-
E.
primaryArmament
Indicates the main weapon or principal offensive system that an entity (such as a vehicle, vessel, or platform) is equipped with or uses.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b47861808190be56a7bbd926e658 |
completed | March 1, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a8a3b08190b4538e119b13f7f5 |
completed | March 1, 2026, 9:42 p.m. |
| PDg | Predicate description generation | batch_69a4b344f6f48190ba03ce593c94176b |
completed | March 1, 2026, 9:44 p.m. |
Created at: March 1, 2026, 7:40 p.m.