Triple
T8828700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CRAM-MD5 |
E210079
|
entity |
| Predicate | usesAlgorithm |
P89
|
FINISHED |
| Object | MD5 |
E192654
|
NE 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: MD5 | Statement: [CRAM-MD5, usesAlgorithm, MD5]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MD5 Context triple: [CRAM-MD5, usesAlgorithm, MD5]
-
A.
MD5
chosen
MD5 is a widely known but now cryptographically broken 128-bit hash function formerly used for checksums, data integrity, and security applications.
-
B.
SHA-1
SHA-1 is a now-legacy 160-bit cryptographic hash function once widely used for data integrity and digital signatures but today considered insecure due to practical collision attacks.
-
C.
Hash
"Hash" is a darkly comic novel by Swedish author Torgny Lindgren that explores memory, identity, and rural life through the story of two men obsessively disputing who makes the better potato hash.
-
D.
RIPEMD-160
RIPEMD-160 is a 160-bit cryptographic hash function designed as an alternative to SHA-1, commonly used for data integrity and security applications.
-
E.
CRAM-MD5
CRAM-MD5 is a challenge–response authentication mechanism that uses MD5 hashing to securely verify a user's identity without transmitting their password in plaintext.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8365b28081909e48e45e95dfc405 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc604c52a48190807e46c15e3c1558 |
completed | April 1, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf896382708190a08c6bacf1157066 |
completed | April 3, 2026, 9:33 a.m. |
Created at: March 30, 2026, 6:47 p.m.