Triple
T560666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fat Man |
E13442
|
entity |
| Predicate | yieldTNTEquivalent |
P6530
|
FINISHED |
| Object | 21000 tons of TNT |
—
|
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: 21000 tons of TNT | Statement: [Fat Man, yieldTNTEquivalent, 21000 tons of TNT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yieldTNTEquivalent Context triple: [Fat Man, yieldTNTEquivalent, 21000 tons of TNT]
-
A.
equivalentTo
chosen
Indicates that two entities represent the same concept, value, or state, and can be treated as interchangeable in the given context.
-
B.
isLegalTenderFor
Indicates that a particular currency or form of money is officially recognized by a governing authority as valid payment for debts and financial transactions within a specified jurisdiction.
-
C.
estimatedTeaWeight
Indicates the quantified amount of tea that is approximated or predicted in weight rather than precisely measured.
-
D.
canBePurchasedWith
Indicates that one entity is able to be bought or acquired using another entity as the form of payment.
-
E.
terminus
Indicates that one entity serves as the final endpoint or stopping place for another entity’s movement, route, or process.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a499e2795c8190903240e79964156d |
completed | March 1, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69a494befb8481908bb4e2e9f31e343b |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.