Triple
T27034042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miss Universe 1987 |
E681002
|
entity |
| Predicate | finalTelecastRuntime |
P72425
|
FINISHED |
| Object | approximately 2 hours |
—
|
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: approximately 2 hours | Statement: [Miss Universe 1987, finalTelecastRuntime, approximately 2 hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalTelecastRuntime Context triple: [Miss Universe 1987, finalTelecastRuntime, approximately 2 hours]
-
A.
televisionSeriesRuntimeCharacteristic
Indicates a relationship where a television series is associated with a specific runtime-related characteristic, such as typical episode length or overall duration pattern.
-
B.
transmissionDuration
Indicates the length of time over which a transmission or transfer of data, signal, or content occurs.
-
C.
runningTimeMiniSeriesVersion
Indicates the duration of the mini-series version of a work, typically measured in time units such as minutes.
-
D.
originalBroadcastLength
chosen
Indicates the duration of time for which something was originally broadcast in its first airing.
-
E.
hasEpisodeRuntime
Indicates the duration of time that each individual episode of a series or show runs.
- 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_69eeeb5566f08190813daf896fa3da04 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 27, 2026, 7:15 a.m.