Triple
T36342610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steam Heat |
E894969
|
entity |
| Predicate | typeOfNumberWithinShow |
P187766
|
FINISHED |
| Object | specialty number |
—
|
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: specialty number | Statement: [Steam Heat, typeOfNumberWithinShow, specialty number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfNumberWithinShow Context triple: [Steam Heat, typeOfNumberWithinShow, specialty number]
-
A.
showType
Indicates the category or format in which something is presented or displayed (e.g., type of show, presentation, or display mode).
-
B.
settingWithinShow
Indicates that one setting (such as a location or environment) exists as part of, or is contained within, a particular show.
-
C.
singsNumberType
chosen
Indicates that an entity performs singing characterized by a specific type or category of number (e.g., musical number or song type).
-
D.
isNumberInAct
Indicates that a specific number appears within, or is associated with, a particular act (such as a legal act, play act, or similar structured unit).
-
E.
numberOfShows
Indicates the total count of shows associated with or performed by a given entity.
- 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_69f76e4e90148190b02fe52593c70b5b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a02fb5ca96081908ff618f560011940 |
completed | May 12, 2026, 10:05 a.m. |
| PD | Predicate disambiguation | batch_6a02f9602b308190a97f81821e12b13f |
completed | May 12, 2026, 9:56 a.m. |
Created at: May 3, 2026, 4:09 p.m.