Triple
T32427518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sokovia disaster |
E828615
|
entity |
| Predicate | inUniverseDateApprox |
P45888
|
FINISHED |
| Object | 2015 |
—
|
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: 2015 | Statement: [Sokovia disaster, inUniverseDateApprox, 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseDateApprox Context triple: [Sokovia disaster, inUniverseDateApprox, 2015]
-
A.
inUniverseDate
chosen
Indicates that an entity is associated with or occurs on a specific date within a fictional or defined universe’s internal timeline.
-
B.
dateApproximate
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
C.
approximateDateChange
Indicates that the date associated with an entity has changed in an inexact or estimated manner rather than to a precisely known new date.
-
D.
unificationApproximateDate
Indicates that two entities became unified or merged around an estimated or approximate date rather than a precisely known time.
-
E.
inUniverseAge
Indicates the age of an entity as measured within the timeline or continuity of a specific fictional or defined universe.
- 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_69f3491b28bc8190b75cea7a507f337b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7626667f48190ad90867eb67ec582 |
completed | May 3, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f76175d6608190b60b268e20f49ed9 |
completed | May 3, 2026, 2:53 p.m. |
Created at: May 1, 2026, 12:54 a.m.