Triple
T31952466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS St. Louis (CL-49) |
E815816
|
entity |
| Predicate | locationOnDate |
P196365
|
FINISHED |
| Object | Pearl Harbor on 1941-12-07 |
—
|
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: Pearl Harbor on 1941-12-07 | Statement: [USS St. Louis (CL-49), locationOnDate, Pearl Harbor on 1941-12-07]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOnDate Context triple: [USS St. Louis (CL-49), locationOnDate, Pearl Harbor on 1941-12-07]
-
A.
hasLocationOnDay
chosen
Indicates that an entity is located at a specific place on a particular calendar day.
-
B.
locatedAtTime
Indicates that a location relationship holds during a specific time or time interval.
-
C.
locationWhenGiven
Indicates the place where an entity is located at the time it is given or transferred to another entity.
-
D.
createdAtLocation
Indicates the place or location where an entity was originally created or brought into existence.
-
E.
mapDate
Indicates a relationship where one value is associated or transformed into a corresponding date representation.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01d9ca07b88190b4ad70b6336447b6 |
completed | May 11, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_6a01d807c3048190b79f0b6b933dd3b7 |
completed | May 11, 2026, 1:22 p.m. |
Created at: May 1, 2026, 12:07 a.m.