Triple
T20069048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penn Linguistics Colloquium |
E499684
|
entity |
| Predicate | timePattern |
P125133
|
FINISHED |
| Object | held once per year |
—
|
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: held once per year | Statement: [Penn Linguistics Colloquium, timePattern, held once per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timePattern Context triple: [Penn Linguistics Colloquium, timePattern, held once per year]
-
A.
timeType
Indicates the specific temporal category or classification associated with a time-related entity or value (e.g., duration, point in time, interval, or recurrence type).
-
B.
timeStructure
Indicates that one entity defines, constrains, or organizes the temporal framework or schedule within which another entity exists or operates.
-
C.
timeNotation
Indicates the specific system or format used to represent and write times (e.g., 12-hour vs 24-hour notation).
-
D.
intervalPattern
chosen
Indicates a recurring temporal relationship where events or states follow a specific, regular interval pattern between their occurrences.
-
E.
timeInterpretation
Indicates how a given temporal expression or event should be understood or interpreted in terms of time (e.g., its reference point, scope, or temporal role).
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e664365ad0819089103b00d1cf8c9f |
completed | April 20, 2026, 5:36 p.m. |
| PD | Predicate disambiguation | batch_69e54cee7a5c819084ae4ff26419833f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:39 p.m.