Triple
T27866211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PDP-9 |
E704365
|
entity |
| Predicate | wordFormat |
P163237
|
FINISHED |
| Object | one sign bit and 17 magnitude bits |
—
|
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: one sign bit and 17 magnitude bits | Statement: [PDP-9, wordFormat, one sign bit and 17 magnitude bits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wordFormat Context triple: [PDP-9, wordFormat, one sign bit and 17 magnitude bits]
-
A.
format
Indicates the specific arrangement, structure, or presentation style in which something is organized or expressed.
-
B.
word
Indicates that one entity is a word (a lexical item) in relation to another entity, such as a language, text, or representation.
-
C.
draftFormatUsed
Indicates that a particular draft was created or prepared using a specified format.
-
D.
cellFormat
Indicates how the visual presentation or styling (such as font, color, borders, or number format) is applied to a cell in a structured layout or table.
-
E.
writingForm
Indicates the specific script, notation, or written representation used to express a piece of language or content.
- 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_69ef840f12408190b539d00d79658abf |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6394830f88190addc152141c50b78 |
completed | May 2, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69f6318be69481909d1bcf29b7b60eb2 |
completed | May 2, 2026, 5:17 p.m. |
| PDg | Predicate description generation | batch_69f6352df6148190bc10772cd40bd7b3 |
completed | May 2, 2026, 5:32 p.m. |
Created at: April 27, 2026, 6:21 p.m.