Triple
T6876410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2010 Haiti earthquake |
E158680
|
entity |
| Predicate | unHeadquartersImpact |
P54339
|
FINISHED |
| Object | collapse of UN headquarters in Port-au-Prince |
—
|
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: collapse of UN headquarters in Port-au-Prince | Statement: [2010 Haiti earthquake, unHeadquartersImpact, collapse of UN headquarters in Port-au-Prince]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unHeadquartersImpact Context triple: [2010 Haiti earthquake, unHeadquartersImpact, collapse of UN headquarters in Port-au-Prince]
-
A.
headquartersFunction
Indicates that an entity serves as the main administrative or central operating location (headquarters) for another entity.
-
B.
affectedCity
Indicates that a particular city is impacted or influenced by a specified event, action, or condition.
-
C.
impactBuilding
Indicates that one entity physically collides with or strikes a building, causing an impact event.
-
D.
nearHeadquartersOf
Indicates that one entity is located geographically close to the headquarters of another entity.
-
E.
infrastructureImpact
chosen
Indicates the effect that an action, event, or entity has on the condition, performance, or availability of infrastructure systems.
- 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_69c68832af1481908ce356e133ebaebe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8cb76108190a5136240ed85d900 |
completed | March 27, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b363dc8190a7225b540ab2bc40 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:22 p.m.