Triple
T4556032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tess Gerritsen |
E120479
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Bloodstream
"Bloodstream" is a medical thriller novel by Tess Gerritsen that blends forensic suspense with small-town mystery and biological danger.
|
E452876
|
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: Bloodstream | Statement: [Tess Gerritsen, notableWork, Bloodstream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bloodstream Context triple: [Tess Gerritsen, notableWork, Bloodstream]
-
A.
Bloodflow
"Bloodflow" is a song by the experimental pop band Dongs of Sevotion.
-
B.
Lifeblood
Lifeblood is a 2004 studio album by Welsh rock band Manic Street Preachers, noted for its sleek, synth-tinged sound and introspective lyrical themes.
-
C.
Lifeblood
Lifeblood is a major expansion for the sci-fi MMORPG EVE Online that introduced significant changes to resource gathering, industry, and player-versus-environment content.
-
D.
Bloods
Bloods is a popular nickname for the Sydney Swans, an Australian Football League club known for its red-and-white colors and strong team culture.
-
E.
Young Blood
"Young Blood" is a classic rhythm and blues song from the 1950s, best known in its hit version by The Coasters and widely covered in rock and roll history.
- 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: Bloodstream Triple: [Tess Gerritsen, notableWork, Bloodstream]
Generated description
"Bloodstream" is a medical thriller novel by Tess Gerritsen that blends forensic suspense with small-town mystery and biological danger.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bloodstream Target entity description: "Bloodstream" is a medical thriller novel by Tess Gerritsen that blends forensic suspense with small-town mystery and biological danger.
-
A.
Bloodflow
"Bloodflow" is a song by the experimental pop band Dongs of Sevotion.
-
B.
Lifeblood
Lifeblood is a 2004 studio album by Welsh rock band Manic Street Preachers, noted for its sleek, synth-tinged sound and introspective lyrical themes.
-
C.
Lifeblood
Lifeblood is a major expansion for the sci-fi MMORPG EVE Online that introduced significant changes to resource gathering, industry, and player-versus-environment content.
-
D.
Bloods
Bloods is a popular nickname for the Sydney Swans, an Australian Football League club known for its red-and-white colors and strong team culture.
-
E.
Young Blood
"Young Blood" is a classic rhythm and blues song from the 1950s, best known in its hit version by The Coasters and widely covered in rock and roll history.
- 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_69bd4636f1648190a701445c2fcd9c17 |
completed | March 20, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69bd5814f56c8190a65f61f6148b7e5a |
completed | March 20, 2026, 2:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdc57d59f88190857cbda79caf3c38 |
completed | March 20, 2026, 10:09 p.m. |
| NEDg | Description generation | batch_69bdc8a14ca88190b4104c113e150edd |
completed | March 20, 2026, 10:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bdc95f7064819081c69df00a869c31 |
completed | March 20, 2026, 10:25 p.m. |
Created at: March 20, 2026, 1:09 p.m.