Triple
T134102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trinity test site, New Mexico |
E2713
|
entity |
| Predicate | timeOfEvent |
P1936
|
FINISHED |
| Object | 05:29:21 local time |
—
|
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: 05:29:21 local time | Statement: [Trinity test site, New Mexico, timeOfEvent, 05:29:21 local time]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfEvent Context triple: [Trinity test site, New Mexico, timeOfEvent, 05:29:21 local time]
-
A.
time
chosen
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
B.
timePeriod
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
C.
timeDescribedAs
Indicates that a specific time or temporal interval is characterized, labeled, or expressed using a particular description or representation.
-
D.
occurredDuring
Indicates that one event or action took place within the temporal span of another event or time period.
-
E.
concludedAtEvent
Indicates that an entity’s participation, state, or validity ended as a result of a specific event.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25788b2688190a45b39447f702551 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.