Triple
T1241018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beirut port explosion of 4 August 2020 |
E26656
|
entity |
| Predicate | blastCraterDiameterApprox |
P18831
|
FINISHED |
| Object | approximately 140 meters |
—
|
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: approximately 140 meters | Statement: [Beirut port explosion of 4 August 2020, blastCraterDiameterApprox, approximately 140 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: blastCraterDiameterApprox Context triple: [Beirut port explosion of 4 August 2020, blastCraterDiameterApprox, approximately 140 meters]
-
A.
craterDiameter
chosen
Indicates the measured width of a crater from one rim edge to the opposite rim edge.
-
B.
craterDepth
Indicates the measured vertical distance from a crater’s rim down to its lowest point.
-
C.
hasCrater
Indicates that one entity possesses or features a crater on its surface.
-
D.
radiusOfSevereDestruction
Indicates the distance from a central point within which damage or destruction is expected to be extremely severe.
-
E.
approximateDiameter
Indicates that one entity specifies the estimated or rough measurement of another entity’s diameter.
- 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_69a4948689d08190b3a4a3f388c02148 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf4343e48190a232abd8475880a0 |
completed | March 1, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69a4bb696a38819095845c84f0241287 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.