Triple
T31100932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daniel Dreiberg |
E792669
|
entity |
| Predicate | predecessorSuperheroIdentity |
P11166
|
FINISHED |
| Object |
Nite Owl I
Nite Owl I is a costumed vigilante from the Watchmen universe, originally active in the 1940s as a founding member of the Minutemen and the inspiration for his successor, Daniel Dreiberg.
|
E1948105
|
NE FINISHED |
How this triple was built (3 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: Nite Owl I | Statement: [Daniel Dreiberg, predecessorSuperheroIdentity, Nite Owl I]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Nite Owl I Triple: [Daniel Dreiberg, predecessorSuperheroIdentity, Nite Owl I]
Generated description
Nite Owl I is a costumed vigilante from the Watchmen universe, originally active in the 1940s as a founding member of the Minutemen and the inspiration for his successor, Daniel Dreiberg.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorSuperheroIdentity Context triple: [Daniel Dreiberg, predecessorSuperheroIdentity, Nite Owl I]
-
A.
predecessorRealName
Indicates that one entity is the real (actual) name of the predecessor of another entity.
-
B.
predecessorAsBlueBeetle
Indicates that one entity is the immediate prior holder of the Blue Beetle mantle or role relative to another entity.
-
C.
predecessorInMyth
Indicates that one mythological figure, story, or element chronologically or narratively comes before and influences or sets the stage for another within a mythic tradition.
-
D.
predecessorName
chosen
Indicates that the value is the name of an entity that directly precedes another in an ordered sequence or lineage.
-
E.
fatherSuperheroIdentity
Indicates that one entity is the father of another entity in the context of their superhero identities.
- F. None of above.
Provenance (6 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_69f224cf157c81909e2d2bd88c9282c3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2938abb0048190912164f6dc0c443a |
completed | June 10, 2026, 10:12 a.m. |
| NEDg | Description generation | batch_6a293cb5308881908eae55ac325f2de5 |
completed | June 10, 2026, 10:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a294246cbfc8190aa6f935fbc146f94 |
completed | June 10, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69fbbd13595c81908719f52c3d37a7e8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: April 29, 2026, 9:03 p.m.