Triple
T12958458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Wall |
E310076
|
entity |
| Predicate | builtWithAllegedAidOf |
P36828
|
FINISHED |
| Object | giants |
—
|
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: giants | Statement: [The Wall, builtWithAllegedAidOf, giants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtWithAllegedAidOf Context triple: [The Wall, builtWithAllegedAidOf, giants]
-
A.
builtWithAssistanceFrom
chosen
Indicates that something was constructed, created, or developed with help, support, or collaboration from another party.
-
B.
allegesCollaborationWith
Indicates that one party claims or asserts that another party has worked together or cooperated with a specified entity.
-
C.
bribedBy
Indicates that an entity has received a bribe from another entity, implying an exchange of value to influence the entity’s actions or decisions.
-
D.
allegedAgentOf
Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
-
E.
allegedUse
Indicates that something is claimed or suspected to have been used, without confirming that the use actually occurred.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97dba57988190b786ffed55687a72 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:44 p.m.