Triple
T38069687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morg |
E950560
|
entity |
| Predicate | servedAsHeraldOf |
P202540
|
FINISHED |
| Object | Galactus |
—
|
NE NERFINISHED |
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: Galactus | Statement: [Morg, servedAsHeraldOf, Galactus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedAsHeraldOf Context triple: [Morg, servedAsHeraldOf, Galactus]
-
A.
servedAs
Indicates that one entity held and performed the role, position, or function associated with another entity for some period of time.
-
B.
hasHeraldicRole
Indicates that an entity holds or is assigned a specific role or function within a heraldic context (such as in coats of arms, armorial bearings, or heraldic ceremonies).
-
C.
alsoServedAs
Indicates that an entity held an additional role or position beyond the primary one already mentioned.
-
D.
servedAsFlagshipFrom
Indicates that an entity functioned as the primary or leading flagship of another entity starting from a specified point in time.
-
E.
servedAsPriestDuring
Indicates that a person held and performed the role or office of a priest during a specified time period or event.
- F. None of above. chosen
Provenance (4 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_69f76f02a6c48190a94f3c0b3ee90cf2 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a008e29f76881908e656dbbd7fceea3 |
completed | May 10, 2026, 1:54 p.m. |
| PD | Predicate disambiguation | batch_6a008dc01b308190bc26e69814692f82 |
completed | May 10, 2026, 1:53 p.m. |
| PDg | Predicate description generation | batch_6a008e29394481909b8d124c8265141f |
completed | May 10, 2026, 1:54 p.m. |
Created at: May 3, 2026, 4:21 p.m.