Triple
T6469080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warehouse 12 at Port of Beirut |
E142301
|
entity |
| Predicate | roleInDisaster |
P31830
|
FINISHED |
| Object | epicenter of the 2020 Beirut port explosion |
—
|
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: epicenter of the 2020 Beirut port explosion | Statement: [Warehouse 12 at Port of Beirut, roleInDisaster, epicenter of the 2020 Beirut port explosion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInDisaster Context triple: [Warehouse 12 at Port of Beirut, roleInDisaster, epicenter of the 2020 Beirut port explosion]
-
A.
hasReliefEffortFrom
Indicates that a party receives assistance or support through a relief effort provided by another party.
-
B.
emergencyRole
chosen
Indicates that an entity holds a specific function, responsibility, or authority in emergency or crisis situations.
-
C.
usedMeansToRescue
Indicates that one entity employed a particular method, tool, or means in order to carry out a rescue.
-
D.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
-
E.
disasterDepicted
Indicates that one entity visually represents or portrays a disaster involving or affecting another entity.
- 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_69c008d3bf4c8190bcf798c5ba9d6fb3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06a16272c81909313455002cd884d |
completed | March 22, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69c0673d46a08190bc8bcd29f9555fe7 |
completed | March 22, 2026, 10:03 p.m. |
Created at: March 22, 2026, 4:49 p.m.