Triple
T13700225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Constantine |
E328495
|
entity |
| Predicate | alias |
P39
|
FINISHED |
| Object |
Conjob
Conjob is a derisive nickname sometimes used for the cynical occult detective and antihero John Constantine from DC Comics.
|
E1056869
|
NE FINISHED |
How this triple was built (4 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: Conjob | Statement: [John Constantine, alias, Conjob]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Conjob Context triple: [John Constantine, alias, Conjob]
-
A.
Bedonkohe
The Bedonkohe are a Western Apache subgroup historically associated with the Mogollon Mountains region of present-day New Mexico.
-
B.
Gedo
Gedo is a region in southwestern Somalia known for its strategic location bordering Kenya and Ethiopia and its role within the federal state of Jubaland.
-
C.
Jochid
The Jochid were the lineage and followers of Jochi, eldest son of Genghis Khan, forming the ruling house of the Golden Horde and other western Mongol domains.
-
D.
Kanuma
Kanuma is a regional harvest festival celebrated mainly in Andhra Pradesh and Telangana as part of the multi-day Makar Sankranti festivities, focusing on cattle worship and agricultural prosperity.
-
E.
Koshun
Koshun is a music producer known for working on projects associated with the artist Amala.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Conjob Triple: [John Constantine, alias, Conjob]
Generated description
Conjob is a derisive nickname sometimes used for the cynical occult detective and antihero John Constantine from DC Comics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Conjob Target entity description: Conjob is a derisive nickname sometimes used for the cynical occult detective and antihero John Constantine from DC Comics.
-
A.
Bedonkohe
The Bedonkohe are a Western Apache subgroup historically associated with the Mogollon Mountains region of present-day New Mexico.
-
B.
Gedo
Gedo is a region in southwestern Somalia known for its strategic location bordering Kenya and Ethiopia and its role within the federal state of Jubaland.
-
C.
Jochid
The Jochid were the lineage and followers of Jochi, eldest son of Genghis Khan, forming the ruling house of the Golden Horde and other western Mongol domains.
-
D.
Kanuma
Kanuma is a regional harvest festival celebrated mainly in Andhra Pradesh and Telangana as part of the multi-day Makar Sankranti festivities, focusing on cattle worship and agricultural prosperity.
-
E.
Koshun
Koshun is a music producer known for working on projects associated with the artist Amala.
- F. None of above. chosen
Provenance (5 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_69d8076ff62081908a7bd79889edd7a0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc879adc88190b03f1cf815b71061 |
completed | April 12, 2026, 4:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d50f34c8190ac5b4e09ab57baa9 |
completed | May 3, 2026, 7:09 p.m. |
| NEDg | Description generation | batch_69f79e77b5e88190a85f4061c8abb8a4 |
completed | May 3, 2026, 7:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f79fa5249481909b2c046ed9801371 |
completed | May 3, 2026, 7:19 p.m. |
Created at: April 9, 2026, 9:54 p.m.