Triple
T28788833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Daghlian |
E726893
|
entity |
| Predicate | receivedRadiationDose |
P125804
|
FINISHED |
| Object | lethal |
—
|
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: lethal | Statement: [Harry Daghlian, receivedRadiationDose, lethal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivedRadiationDose Context triple: [Harry Daghlian, receivedRadiationDose, lethal]
-
A.
typicalOccupationalDoseLimitPerYear
Indicates the standard maximum amount of radiation dose that a worker is normally allowed to receive in one year as part of their occupation.
-
B.
radiationLevel
chosen
Indicates the intensity or amount of radiation present in or emitted by an entity or environment.
-
C.
usesRadiation
Indicates that an entity employs radiation as a means or component in performing an action, process, or function.
-
D.
radiationToleranceTotalIonizingDose
Indicates the maximum total ionizing radiation dose an entity can withstand before its performance or integrity is adversely affected.
-
E.
equalsInAbsorbedDoseTo
Indicates that two entities have the same value or level in terms of absorbed dose (e.g., radiation dose received).
- 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_69f0319aabec81908368720196f69a35 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 28, 2026, 6:22 a.m.