Triple
T36725562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lauds for the Dead |
E907184
|
entity |
| Predicate | hasCanonicalHourType |
P201201
|
FINISHED |
| Object | Lauds |
—
|
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: Lauds | Statement: [Lauds for the Dead, hasCanonicalHourType, Lauds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanonicalHourType Context triple: [Lauds for the Dead, hasCanonicalHourType, Lauds]
-
A.
hasNonIntegerHourOffset
Indicates that the time-related value or time zone differs from a reference time by an offset that is not a whole number of hours (e.g., includes 30- or 45-minute increments).
-
B.
hasCanonicalDayBeginning
Indicates that there is a designated, standard starting point of the day defined for a given context or system.
-
C.
isWholeHourOffset
Indicates that the time zone or time offset differs from a reference time (typically UTC) by an exact whole number of hours, with no fractional minutes involved.
-
D.
hasStandardTimeUTCOffset
Indicates the fixed difference in hours and minutes between an entity’s standard (non-daylight-saving) local time and Coordinated Universal Time (UTC).
-
E.
hasHalfHourOffset
Indicates that one entity’s time zone differs from another’s by an offset that includes a 30-minute (half-hour) component.
- F. None of above. chosen
Provenance (4 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_69f76e746e4c8190a0d05cc6d57a643e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffde9263248190996f970b6cf6e49d |
completed | May 10, 2026, 1:25 a.m. |
| PD | Predicate disambiguation | batch_69ffdd760f1c8190abc6c0c1cd97ba5f |
completed | May 10, 2026, 1:20 a.m. |
| PDg | Predicate description generation | batch_69ffde916fcc81908d6e1b4e6d3f761c |
completed | May 10, 2026, 1:25 a.m. |
Created at: May 3, 2026, 4:12 p.m.