Triple
T27692282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TLS heartbeat extension |
E698189
|
entity |
| Predicate | messageDirection |
P140870
|
FINISHED |
| Object | bidirectional |
—
|
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: bidirectional | Statement: [TLS heartbeat extension, messageDirection, bidirectional]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: messageDirection Context triple: [TLS heartbeat extension, messageDirection, bidirectional]
-
A.
communicationDirection
Indicates the directional flow of a communication act, specifying who is sending information and who is receiving it.
-
B.
mediaDirection
Indicates the direction or flow of media transmission between entities, such as who is sending and who is receiving the media.
-
C.
transmissionDirection
chosen
Indicates the direction in which something is transmitted or passed from one entity to another.
-
D.
connectionDirection
Indicates the directional flow or orientation of a connection from one entity to another.
-
E.
packetDirection
Indicates the direction in which a data packet is traveling between network endpoints (e.g., inbound or outbound).
- 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63578a9cc8190a1f75ca0afbca964 |
completed | May 2, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:52 p.m.