Triple
T22457690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HAZOP |
E555155
|
entity |
| Predicate | inputDocument |
P3129
|
FINISHED |
| Object | Piping and Instrumentation Diagram |
—
|
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: Piping and Instrumentation Diagram | Statement: [HAZOP, inputDocument, Piping and Instrumentation Diagram]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inputDocument Context triple: [HAZOP, inputDocument, Piping and Instrumentation Diagram]
-
A.
publicDocument
Indicates that a document is officially available to the general public without access restrictions.
-
B.
documentSource
Indicates that one entity serves as the origin, provider, or provenance source for a given document.
-
C.
usedDocument
chosen
Indicates that one entity has employed, referenced, or otherwise made use of a particular document in performing an action or fulfilling a purpose.
-
D.
documentsNow
Indicates that an entity is currently documenting, recording, or writing about another entity at the present time.
-
E.
documentNumber
Indicates the unique identifying number assigned to a specific document in the relationship.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7d00208190955a70e2c22d25a4 |
completed | April 29, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:48 p.m.