Triple
T438263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Tower of the World Trade Center |
E10057
|
entity |
| Predicate | impactTime |
P1936
|
FINISHED |
| Object | 2001-09-11T08:46:30-04:00 |
—
|
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: 2001-09-11T08:46:30-04:00 | Statement: [North Tower of the World Trade Center, impactTime, 2001-09-11T08:46:30-04:00]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactTime Context triple: [North Tower of the World Trade Center, impactTime, 2001-09-11T08:46:30-04:00]
-
A.
time
chosen
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
B.
timescale
Indicates the temporal scale or duration over which a process, relationship, or effect occurs or is evaluated.
-
C.
attackDate
Indicates the calendar date on which an attack or assault event took place.
-
D.
deploymentTime
Indicates the point in time at which something is deployed, initiated, or put into operation.
-
E.
firstSuccessfulImpactBy
Indicates that one entity is the earliest or initial successful impactor upon another entity in a given context or sequence of events.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef283be881909444aaf257451747 |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2eddb98e081909efcf9f0a955a908 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.