Triple

T12552822
Position Surface form Disambiguated ID Type / Status
Subject ASTM C33 E300136 entity
Predicate relatedTo P37 FINISHED
Object ASTM C87
ASTM C87 is a standard specification issued by ASTM International that defines requirements and test methods for chemical admixtures used in concrete.
E1017289 NE FINISHED

How this triple was built (4 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: ASTM C87 | Statement: [ASTM C33, relatedTo, ASTM C87]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ASTM C87
Context triple: [ASTM C33, relatedTo, ASTM C87]
  • A. ASTM C187
    ASTM C187 is a standardized test method that specifies how to determine the normal consistency (standard water requirement) of hydraulic cement paste.
  • B. ASTM C188
    ASTM C188 is a standard test method that specifies procedures for determining the density (specific gravity) of hydraulic cement.
  • C. ASTM C91
    ASTM C91 is a standard specification issued by ASTM International that defines the requirements for masonry cement used in construction applications.
  • D. ASTM C451
    ASTM C451 is a standard test method published by ASTM International that specifies procedures for determining the early stiffening (false set) of hydraulic cement.
  • E. ASTM C115
    ASTM C115 is a standard test method that specifies procedures for determining the fineness of Portland cement by the turbidimetric method.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: ASTM C87
Triple: [ASTM C33, relatedTo, ASTM C87]
Generated description
ASTM C87 is a standard specification issued by ASTM International that defines requirements and test methods for chemical admixtures used in concrete.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ASTM C87
Target entity description: ASTM C87 is a standard specification issued by ASTM International that defines requirements and test methods for chemical admixtures used in concrete.
  • A. ASTM C187
    ASTM C187 is a standardized test method that specifies how to determine the normal consistency (standard water requirement) of hydraulic cement paste.
  • B. ASTM C188
    ASTM C188 is a standard test method that specifies procedures for determining the density (specific gravity) of hydraulic cement.
  • C. ASTM C91
    ASTM C91 is a standard specification issued by ASTM International that defines the requirements for masonry cement used in construction applications.
  • D. ASTM C451
    ASTM C451 is a standard test method published by ASTM International that specifies procedures for determining the early stiffening (false set) of hydraulic cement.
  • E. ASTM C115
    ASTM C115 is a standard test method that specifies procedures for determining the fineness of Portland cement by the turbidimetric method.
  • F. None of above. chosen

Provenance (5 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9548444d081908f00cea1ce7032c7 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbb096d881908dfd2a7126632d96 completed May 3, 2026, 4:14 a.m.
NEDg Description generation batch_69f6cd3d5090819091b65f544ad139fd completed May 3, 2026, 4:21 a.m.
NED2 Entity disambiguation (via description) batch_69f6cdc8d52c819083717a455d589646 completed May 3, 2026, 4:23 a.m.
Created at: April 8, 2026, 9:58 p.m.