Triple
T6670241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HT |
E151707
|
entity |
| Predicate | preferredCapitalization |
P72382
|
FINISHED |
| Object | uppercase |
—
|
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: uppercase | Statement: [HT, preferredCapitalization, uppercase]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preferredCapitalization Context triple: [HT, preferredCapitalization, uppercase]
-
A.
possibleCapital
Indicates that a location is a candidate or potential capital city of a given political or administrative entity.
-
B.
capitalizedOn
Indicates that one entity took advantage of, exploited, or made beneficial use of an opportunity, situation, or resource provided or created by another entity.
-
C.
precededByCapital
Indicates that the referenced element is immediately preceded by a capital letter.
-
D.
isCapitalised
Indicates that a given string or word is written with its first letter in uppercase (and the rest in lowercase, if applicable).
-
E.
isCapitalizationWeighted
Indicates that something is evaluated or adjusted based on the relative capitalization (size or value of capital) of its components.
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
| PDg | Predicate description generation | batch_69c6ce72809c8190be85f6e42ca1c8ea |
completed | March 27, 2026, 6:37 p.m. |
Created at: March 27, 2026, 2:02 p.m.