Triple
T33954661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magnus Pym |
E870534
|
entity |
| Predicate | hasSecretAllegiance |
P91605
|
FINISHED |
| Object | foreign intelligence service in the novel |
—
|
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: foreign intelligence service in the novel | Statement: [Magnus Pym, hasSecretAllegiance, foreign intelligence service in the novel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecretAllegiance Context triple: [Magnus Pym, hasSecretAllegiance, foreign intelligence service in the novel]
-
A.
hadAllegiance
Indicates that an entity was loyally committed or formally bound in support or service to another entity, such as a person, group, or cause.
-
B.
namedForAllegiance
Indicates that an entity is named in reference to, or in honor of, a particular allegiance, affiliation, or loyalty.
-
C.
hasAuthorAllegiance
Indicates that an author is affiliated with, loyal to, or aligned with a particular group, organization, cause, or ideology.
-
D.
hadAllegianceDuring
Indicates that an entity was formally loyal or committed to another entity for a specified period of time.
-
E.
secretAffiliation
chosen
Indicates a hidden or undisclosed association, membership, or allegiance that one entity has with another.
- 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_69f3499c2d7481909c953a5010227725 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff97637ad881908c24fe2cc6b036db |
completed | May 9, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69ff96c43a808190942eeda1934602db |
completed | May 9, 2026, 8:19 p.m. |
Created at: May 1, 2026, 1:49 a.m.